A subway station air conditioning energy-saving control device based on monitoring video

Abstract

The utility model discloses a subway station air conditioning energy -conserving control device based on monitoring video, and the device includes monitoring camera group, video signal transmission network, image processing unit, central control unit, air supply temperature control device, refrigerated water flow control device and air supply wind speed adjusting device. Monitoring camera group real -time acquisition personnel distribution video data in the station, and after image recognition to image processing unit, will result send to central control unit. Central control unit generates control instruction according to built -in energy -conserving strategy, and the air supply temperature, refrigerated water flow and air supply wind speed are adjusted synchronously, make the output of air conditioning system and the personnel load of dynamic change in the station match. The utility model overcomes the problem of traditional control mode lag, and realized the accurate cooling on demand, and effectively reduced the energy consumption of subway station air conditioning system.

Description

Technical Field

[0001] This utility model relates to the field of air conditioning load operation and maintenance equipment for underground stations, and in particular to an energy-saving control device for subway station air conditioning based on monitoring video. Background Technology

[0002] As semi-enclosed underground spaces, subway stations rely heavily on air conditioning systems for environmental control. Due to high passenger volume, relatively enclosed spaces, and complex heat sources such as train piston winds and equipment heat dissipation, the air conditioning system must handle enormous cooling and fresh air loads. Current design standards generally use the maximum passenger density under extreme conditions (such as peak hour passenger flow) as the load calculation benchmark, resulting in a redundancy of 1.5-2 times in the selected air conditioning equipment capacity. However, in actual operation, subway station passenger flow exhibits significant spatiotemporal fluctuations: the instantaneous passenger density can vary by 5-10 times between weekday morning and evening peak hours and off-peak hours, and between different areas (such as platforms and passageways). This extensive approach of "designing based on maximum load and operating based on average load" leaves the air conditioning system in a state of long-term inefficient operation. Statistics show that air conditioning energy consumption accounts for more than 40% of the total energy consumption of subway stations, with approximately 30% of this energy waste stemming from a mismatch between fresh air volume and actual demand. Furthermore, traditional control strategies rely on fixed schedules or manual experience, making it difficult to respond promptly to sudden changes in passenger flow (such as during holidays or large-scale events), which can easily lead to localized areas being too cold or too hot, or experiencing a decline in air quality. Therefore, how to achieve energy conservation and consumption reduction by dynamically adjusting air conditioning parameters (such as fresh air volume and supply air temperature) while ensuring thermal comfort and air quality has become a critical issue that urgently needs to be addressed in subway operations.

[0003] Currently, energy-saving operation devices and control methods for subway station air conditioning generally suffer from insufficient adaptability. Most existing solutions rely on passenger count identification for air conditioning operation adjustment, estimating the total number of passengers in the concourse or platform through video monitoring or passenger flow statistics, and then adjusting operating parameters such as supply air temperature and fresh air volume according to preset passenger density thresholds. However, this type of method only reflects the "number of people" in the space, ignoring individual differences in passengers' thermal perception and actual thermal needs. Under the same environmental conditions, different passengers may exhibit significant differences due to factors such as clothing, activity level, and health status—some may feel stuffy, while others may feel cold. Judging heating and cooling needs solely based on the number of people can easily lead to inaccurate control. Another type of indirect inference method based on environmental sensors (such as CO2 concentration, temperature, and humidity) also has limitations. CO2 concentration requires a certain amount of time to accumulate before reflecting changes in personnel, resulting in a response delay. Furthermore, single-point or small-scale sensors cannot accurately represent the distribution of people and differences in heating and cooling needs within a large space. In addition, these methods are mostly based on real-time feedback control in their control logic, lacking time weighting and historical data update mechanisms, and cannot comprehensively consider short-term fluctuations and long-term trends. For example, when passenger numbers or heat demand fluctuate abnormally in the short term, the system often adjusts frequently, leading to increased energy consumption or decreased comfort. However, if the prediction results can be smoothed based on weighted historical values, the stability and accuracy of the control can be significantly improved. Existing solutions also generally lack in-depth analysis of passenger action characteristics at the algorithm level, such as failing to identify passengers' actions related to cooling or heating needs, such as fanning, wiping sweat, or crossing their arms, resulting in a disconnect between air conditioning control and passengers' actual experience. In summary, most current energy-saving operation devices for subway station air conditioning neglect the dynamic weighted updates of individualized passenger heat demands and the time dimension, making it difficult to achieve truly precise, energy-saving, and comfort-oriented operation control. Utility Model Content

[0004] The purpose of this invention is to provide a subway station air conditioning energy-saving control device based on video surveillance. Through integrated hardware linkage control, it can achieve fine adjustment of the subway station air conditioning system, significantly reduce air conditioning energy consumption and improve system operating efficiency while ensuring passenger comfort.

[0005] The technical solution adopted in this utility model is:

[0006] A subway station air conditioning energy-saving control device based on surveillance video, comprising:

[0007] A surveillance camera array is used to collect real-time video data on the distribution of people within subway stations;

[0008] A video signal transmission network that connects to the surveillance camera array to transmit video data;

[0009] The image processing unit is connected to the video signal transmission network and is used to receive video data and perform image recognition processing.

[0010] The central control unit, connected to the image processing unit, is used to receive the image recognition processing results from the image processing unit and output control commands.

[0011] The air supply temperature control device is connected to the central control unit and is used to receive control commands and adjust the air supply temperature of the air conditioning system.

[0012] Chilled water flow control device, connected to the central control unit, is used to receive control commands and adjust the chilled water flow of the air conditioning system;

[0013] It also includes an air supply speed adjustment device, which is connected to the central control unit to receive control commands and adjust the air supply speed of the air conditioning system.

[0014] Furthermore, the surveillance camera group includes two or more high-definition cameras, which are distributed and installed in the concourse and platform levels of the subway station.

[0015] Specifically, the high-definition camera has a resolution of 1080P or higher and a video acquisition capability of no less than 25 frames per second, and may further include an infrared thermal imaging camera to assist in collecting personnel's body surface temperature information and enhance the accuracy of thermal demand identification. The temperature measurement accuracy of the infrared thermal imaging camera is no less than ±0.3℃, and the temperature measurement range is -20℃ to +60℃.

[0016] Furthermore, the video signal transmission network adopts gigabit Ethernet or fiber optic transmission to ensure the real-time performance and integrity of video data.

[0017] Furthermore, the image processing unit is configured to perform personnel density recognition and thermal demand recognition on the video data. The image processing unit has GPU-accelerated computing capabilities and supports parallel processing of multiple video streams.

[0018] Furthermore, the central control unit has a built-in preset energy-saving strategy, and the central control unit is configured to generate control commands according to the preset energy-saving strategy.

[0019] Furthermore, the central control unit includes a core processor for executing control logic and data processing; a data storage device for storing historical data and operating strategies; and input / output interfaces for data communication with various control devices. The decision-making algorithm module employs fuzzy logic control or reinforcement learning algorithms to perform multi-objective optimization decisions based on passenger density information and thermal demand probability, maximizing energy savings while ensuring passenger comfort.

[0020] Specifically, the central control unit adopts a distributed control architecture, supporting independent control of multiple areas. The core processor uses an ARM Cortex-A78 or Intel Core i7 or higher-level processor with a clock speed of at least 2.0GHz, used to execute complex control logic and data processing. Data storage includes at least 16GB of RAM and at least 512GB of storage space, used to store massive amounts of historical data, energy-saving operation strategies, and machine learning model parameters. Input / output interfaces include Ethernet, RS485, and CAN bus interfaces for high-speed, stable data communication with various control devices. The core processor employs advanced fuzzy logic control or reinforcement learning algorithms to make multi-objective optimization decisions based on passenger density information and thermal demand probability, maximizing energy savings while ensuring passenger thermal comfort.

[0021] Furthermore, the air supply temperature control device includes: a temperature sensor for real-time monitoring of the air supply temperature; and a temperature regulation actuator for adjusting the air supply temperature according to control commands, wherein the temperature regulation actuator is preferably an electric valve or a frequency converter.

[0022] Specifically, the temperature sensor uses a PT1000 platinum resistance thermometer or a thermocouple sensor, with a measurement accuracy of not less than ±0.2℃ and a response time of not more than 5 seconds; the temperature regulation actuator includes an electric regulating valve and a frequency converter, the electric regulating valve has an adjustment accuracy of not less than 1%, the frequency converter supports 0-50Hz frequency adjustment with an adjustment accuracy of not less than 0.1Hz, and the overall control accuracy is not less than ±0.5℃.

[0023] Furthermore, the chilled water flow control device includes: a chilled water pump for providing power for chilled water circulation; an electric regulating valve for adjusting the chilled water flow according to control commands; and a flow sensor, employing an electromagnetic flow meter or an ultrasonic flow meter with a measurement accuracy of not less than ±1%, for real-time monitoring of chilled water flow and providing feedback signals.

[0024] Specifically, the chilled water pump is a variable frequency speed control pump with a power range of 5-200kW and an efficiency of not less than 85%; the electric regulating valve is a proportional-integral regulating valve with a regulation ratio of not less than 50:1 and a leakage level of not less than Class IV, used to accurately regulate the chilled water flow rate according to control commands; the flow sensor is an electromagnetic flow meter or an ultrasonic flow meter with a measurement accuracy of not less than ±1%, used to monitor the chilled water flow rate in real time and provide feedback signals, with an overall flow rate regulation range of 20%-100% of the rated flow rate.

[0025] Furthermore, the air supply speed adjustment device includes: a variable frequency fan for adjusting the air supply speed; a jet-induced fan unit configured in densely populated areas of the subway station to assist diffusion; and a wind speed sensor, which adopts a thermal wind speed sensor or an ultrasonic wind speed sensor with a measurement range of 0-10m / s and an accuracy of not less than ±3%, for real-time monitoring of the air supply speed.

[0026] Specifically, the variable frequency fan adopts an EC motor or a permanent magnet synchronous motor with a power range of 1-50kW and an efficiency of not less than 90%, supporting stepless speed regulation; the jet-induced fan unit includes multiple small-power induced fans, with a single unit power of 0.5-2kW, used to assist in airflow organization and diffusion in areas with high personnel density; the wind speed sensor adopts a thermal wind speed sensor or an ultrasonic wind speed sensor with a measurement range of 0-10m / s and an accuracy of not less than ±3%, used to monitor the supply wind speed in real time, and the overall wind speed adjustment range is 0.1-3.0m / s.

[0027] This utility model may also include an environmental parameter monitoring device connected to the central control unit, used to monitor environmental parameters such as temperature, humidity, CO2 concentration, and PM2.5 concentration in the subway station, providing environmental background data to the central control unit and improving the accuracy of heat demand judgment.

[0028] Furthermore, it also includes a human-machine interface connected to the central control unit. The human-machine interface includes: a display module, which uses a touch screen of no less than 15 inches, for real-time display of system operating status, personnel distribution, heat demand analysis results, and energy consumption data; an operation module, which supports touch operation and voice control, for receiving manual control commands and parameter settings; and an alarm module, which is used to issue audible and visual alarm signals when the system is abnormal or the equipment fails.

[0029] This utility model may also include a data communication device that supports 4G / 5G wireless communication and Ethernet wired communication, used for data exchange with the subway operation management center to achieve remote monitoring and centralized management. Data transmission uses the AES256 encryption algorithm to ensure security.

[0030] This utility model adopts the above technical solution and has the following advantages:

[0031] (1) Without relying on fixed thresholds or human experience, the system automatically adjusts the control strategy by sensing environmental changes in real time (such as population density and equipment status), achieving closed-loop optimization from data acquisition to decision execution, and ensuring that the system always matches actual needs with optimal efficiency.

[0032] (2) Directly reuse existing monitoring equipment data, eliminating the complexity of additional sensor deployment and multi-system data docking, reducing hardware investment and maintenance costs, while reducing control delay caused by data silos and improving the accuracy of resource allocation.

[0033] (3) With thermal comfort as a constraint, priority is given to ensuring the temperature control stability of the area where people are active. At the same time, excessive cooling is avoided by dynamically adjusting the output of the equipment, taking into account both energy-saving goals and actual user perception, and improving the overall service quality. Attached Figure Description

[0034] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments;

[0035] Figure 1 This is a schematic diagram of the structure of a subway station air conditioning energy-saving control device based on surveillance video, according to this utility model. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0037] like Figure 1 As shown, this utility model discloses an energy-saving control device for subway station air conditioning based on surveillance video, which includes:

[0038] A surveillance camera array is used to collect real-time video data on the distribution of people within subway stations;

[0039] A video signal transmission network that connects to the surveillance camera array to transmit video data;

[0040] The image processing unit is connected to the video signal transmission network and is used to receive video data and perform image recognition processing.

[0041] The central control unit, connected to the image processing unit, is used to receive the image recognition processing results from the image processing unit and output control commands.

[0042] The air supply temperature control device is connected to the central control unit and is used to receive control commands and adjust the air supply temperature of the air conditioning system.

[0043] Chilled water flow control device, connected to the central control unit, is used to receive control commands and adjust the chilled water flow of the air conditioning system;

[0044] It also includes an air supply speed adjustment device, which is connected to the central control unit to receive control commands and adjust the air supply speed of the air conditioning system.

[0045] Furthermore, the surveillance camera group includes two or more high-definition cameras, which are distributed and installed in the concourse and platform levels of the subway station.

[0046] Specifically, the high-definition camera has a resolution of 1080P or higher and a video acquisition capability of no less than 25 frames per second, and may further include an infrared thermal imaging camera to assist in collecting personnel's body surface temperature information and enhance the accuracy of thermal demand identification. The temperature measurement accuracy of the infrared thermal imaging camera is no less than ±0.3℃, and the temperature measurement range is -20℃ to +60℃.

[0047] Furthermore, the video signal transmission network adopts gigabit Ethernet or fiber optic transmission to ensure the real-time performance and integrity of video data.

[0048] Furthermore, the image processing unit is configured to perform personnel density recognition and thermal demand recognition on the video data. The image processing unit has GPU-accelerated computing capabilities and supports parallel processing of multiple video streams.

[0049] Furthermore, the central control unit has a built-in preset energy-saving strategy, and the central control unit is configured to generate control commands according to the preset energy-saving strategy.

[0050] Furthermore, as a feasible implementation, this utility model can use personnel density and thermal demand as the control objects. The image processing unit includes a personnel density recognition processor and a thermal demand recognition processor; the personnel density recognition processor is equipped with a mature target detection algorithm in the prior art, and the personnel density recognition processor performs image preprocessing, target detection and multi-frame tracking on video data through the target detection algorithm to calculate the number of people and personnel density in each area;

[0051] The thermal demand recognition processor is equipped with mature pose estimation and behavior recognition algorithms in the existing technology. The thermal demand recognition processor analyzes the passenger action features in video data through pose estimation and behavior recognition algorithms to assess the probability of passengers' thermal demand.

[0052] Specifically, as a feasible implementation, the personnel density recognition processor employs a deep learning-based YOLOv5 or higher object detection algorithm. The thermal demand recognition processor employs deep learning-based pose estimation and behavior recognition algorithms, capable of identifying specific action patterns related to thermal sensation.

[0053] Furthermore, as an optional implementation, the thermal demand recognition processor integrates a pose estimation module, an action recognition module, a feature extraction module, a probability evaluation module, and a multi-view fusion module. The pose estimation module uses OpenPose or HRNet algorithms to detect key points of the human body in the video, including no fewer than 17 human key points such as the head, neck, and shoulders. This module provides high-precision basic data for subsequent action analysis by accurately capturing the human skeletal structure.

[0054] The action recognition module is based on a 3D convolutional neural network or Transformer architecture. It performs temporal analysis on changes in key human body points in consecutive frames to identify preset actions related to heat demand, including but not limited to: waving hands, fanning oneself, wiping sweat, loosening collars, and frequent movement; as well as actions related to cold demand, such as rubbing hands, crossing arms, curling up, and stomping feet. This module can learn the spatiotemporal characteristics of actions and determine what preset actions the passenger is performing.

[0055] The feature extraction module extracts quantitative features from the identified actions, including parameters such as action frequency, action amplitude, action duration, and rate of change of body posture. These features are key to quantifying passengers' thermal sensation. The probability assessment module uses machine learning algorithms such as support vector machines, random forests, or neural networks to fuse the extracted action features with environmental parameters, outputting a probability value for hot or cold demand between 0 and 1, where 0.0-0.3 represents cold demand, 0.3-0.7 represents a comfortable state, and 0.7-1.0 represents hot demand. The probability assessment module also has an adaptive learning function, which can continuously optimize the thermal demand recognition model based on historical operating data and passenger feedback. The model accuracy increases with operating time, and the recognition accuracy is no less than 90% after 6 months of operation. The multi-view fusion module integrates video data from different monitoring cameras, eliminates the influence of single-view occlusion through 3D reconstruction technology, and improves the accuracy of human posture estimation. The posture estimation accuracy after multi-view fusion is improved by no less than 15%.

[0056] Furthermore, the central control unit includes a core processor for executing control logic and data processing; a data storage device for storing historical data and operating strategies; and input / output interfaces for data communication with various control devices. The decision-making algorithm module employs fuzzy logic control or reinforcement learning algorithms to perform multi-objective optimization decisions based on passenger density information and thermal demand probability, maximizing energy savings while ensuring passenger comfort.

[0057] Specifically, the central control unit adopts a distributed control architecture, supporting independent control of multiple areas. The core processor uses an ARM Cortex-A78 or Intel Core i7 or higher-level processor with a clock speed of at least 2.0GHz, used to execute complex control logic and data processing. Data storage includes at least 16GB of RAM and at least 512GB of storage space, used to store massive amounts of historical data, energy-saving operation strategies, and machine learning model parameters. Input / output interfaces include Ethernet, RS485, and CAN bus interfaces for high-speed, stable data communication with various control devices. The core processor employs advanced fuzzy logic control or reinforcement learning algorithms to make multi-objective optimization decisions based on passenger density information and thermal demand probability, maximizing energy savings while ensuring passenger thermal comfort.

[0058] Furthermore, the air supply temperature control device includes: a temperature sensor for real-time monitoring of the air supply temperature; and a temperature regulation actuator for adjusting the air supply temperature according to control commands, wherein the temperature regulation actuator is preferably an electric valve or a frequency converter.

[0059] Specifically, the temperature sensor uses a PT1000 platinum resistance thermometer or a thermocouple sensor, with a measurement accuracy of not less than ±0.2℃ and a response time of not more than 5 seconds; the temperature regulation actuator includes an electric regulating valve and a frequency converter, the electric regulating valve has an adjustment accuracy of not less than 1%, the frequency converter supports 0-50Hz frequency adjustment with an adjustment accuracy of not less than 0.1Hz, and the overall control accuracy is not less than ±0.5℃.

[0060] Furthermore, the chilled water flow control device includes: a chilled water pump for providing power for chilled water circulation; an electric regulating valve for adjusting the chilled water flow according to control commands; and a flow sensor, employing an electromagnetic flow meter or an ultrasonic flow meter with a measurement accuracy of not less than ±1%, for real-time monitoring of chilled water flow and providing feedback signals.

[0061] Specifically, the chilled water pump is a variable frequency speed control pump with a power range of 5-200kW and an efficiency of not less than 85%; the electric regulating valve is a proportional-integral regulating valve with a regulation ratio of not less than 50:1 and a leakage level of not less than Class IV, used to accurately regulate the chilled water flow rate according to control commands; the flow sensor is an electromagnetic flow meter or an ultrasonic flow meter with a measurement accuracy of not less than ±1%, used to monitor the chilled water flow rate in real time and provide feedback signals, with an overall flow rate regulation range of 20%-100% of the rated flow rate.

[0062] Furthermore, the air supply speed adjustment device includes: a variable frequency fan for adjusting the air supply speed; a jet-induced fan unit configured in densely populated areas of the subway station to assist diffusion; and a wind speed sensor, which adopts a thermal wind speed sensor or an ultrasonic wind speed sensor with a measurement range of 0-10m / s and an accuracy of not less than ±3%, for real-time monitoring of the air supply speed.

[0063] Specifically, the variable frequency fan adopts an EC motor or a permanent magnet synchronous motor with a power range of 1-50kW and an efficiency of not less than 90%, supporting stepless speed regulation; the jet-induced fan unit includes multiple small-power induced fans, with a single unit power of 0.5-2kW, used to assist in airflow organization and diffusion in areas with high personnel density; the wind speed sensor adopts a thermal wind speed sensor or an ultrasonic wind speed sensor with a measurement range of 0-10m / s and an accuracy of not less than ±3%, used to monitor the supply wind speed in real time, and the overall wind speed adjustment range is 0.1-3.0m / s.

[0064] This utility model may also include an environmental parameter monitoring device connected to the central control unit, used to monitor environmental parameters such as temperature, humidity, CO2 concentration, and PM2.5 concentration in the subway station, providing environmental background data to the central control unit and improving the accuracy of heat demand judgment.

[0065] Furthermore, it also includes a human-machine interface connected to the central control unit. The human-machine interface includes: a display module, which uses a touch screen of no less than 15 inches, for real-time display of system operating status, personnel distribution, heat demand analysis results, and energy consumption data; an operation module, which supports touch operation and voice control, for receiving manual control commands and parameter settings; and an alarm module, which is used to issue audible and visual alarm signals when the system is abnormal or the equipment fails.

[0066] This utility model may also include a data communication device that supports 4G / 5G wireless communication and Ethernet wired communication, used for data exchange with the subway operation management center to achieve remote monitoring and centralized management. Data transmission uses the AES256 encryption algorithm to ensure security.

[0067] The device of this utility model also has a regional control function according to specific needs, which can divide the subway station into multiple independent control areas. Each area can independently adjust the air conditioning parameters according to the population density and heat demand probability of the area, so as to achieve refined energy-saving control. Compared with the traditional unified control method, the energy-saving effect is improved by no less than 20%.

[0068] As a feasible operational control scheme, air conditioning energy-saving control is implemented based on personnel density and the probability of passengers' thermal demand. Specifically, when the system is operational, a monitoring camera group continuously collects video data from the subway station and transmits it to the image processing unit via a video signal transmission network. The image processing unit analyzes the video data in real time, identifying the personnel density and the probability of passengers' thermal demand in each area. This information is then sent to the central control unit. Based on the received real-time data, combined with its internally stored energy-saving operation strategies and historical data, the central control unit intelligently calculates the optimal setpoints for supply air temperature, chilled water flow rate, and supply air velocity, and generates corresponding control commands. These commands are sent to the supply air temperature control device, chilled water flow rate control device, and supply air velocity adjustment device, respectively. Each actuator precisely adjusts the corresponding parameters of the air conditioning system according to the received commands, thereby achieving dynamic and refined control of the air conditioning system.

[0069] For example, when the population density in a certain area increases and the probability of heat demand increases, the central control unit will instruct the air supply temperature control device to lower the air supply temperature, instruct the chilled water flow control device to increase the chilled water flow, and instruct the air supply speed regulation device to increase the air supply speed, so as to quickly respond to load changes, ensure passenger comfort, and achieve energy saving. Through this closed-loop control, this invention can significantly reduce the energy consumption of the subway station air conditioning system while improving the passenger comfort experience.

[0070] This invention utilizes a surveillance camera array to collect real-time video data on the distribution of people within subway stations. The data is transmitted via a video signal transmission network to an image processing unit for personnel density and thermal demand identification. The image processing unit then sends the identification results to a central control unit. Based on the received data and a preset energy-saving operation strategy, the central control unit generates control commands and sends them to the air supply temperature control device, chilled water flow control device, and air supply speed adjustment device to dynamically adjust the air supply temperature, chilled water flow, and air supply speed of the air conditioning system. Through integrated hardware design and intelligent linkage control, this invention achieves refined and dynamic adjustment of the subway station air conditioning system, significantly reducing air conditioning energy consumption and improving system operating efficiency while ensuring passenger comfort.

[0071] This utility model adopts the above technical solution and has the following advantages:

[0072] (1) Without relying on fixed thresholds or human experience, the system automatically adjusts the control strategy by sensing environmental changes in real time (such as population density and equipment status), achieving closed-loop optimization from data acquisition to decision execution, and ensuring that the system always matches actual needs with optimal efficiency.

[0073] (2) Directly reuse existing monitoring equipment data, eliminating the complexity of additional sensor deployment and multi-system data docking, reducing hardware investment and maintenance costs, while reducing control delay caused by data silos and improving the accuracy of resource allocation.

[0074] (3) With thermal comfort as a constraint, priority is given to ensuring the temperature control stability of the area where people are active. At the same time, excessive cooling is avoided by dynamically adjusting the output of the equipment, taking into account both energy-saving goals and actual user perception, and improving the overall service quality.

[0075] This invention overcomes the problems of lag and over-adjustment in traditional control methods, and achieves precise cooling on demand, effectively reducing the energy consumption of subway station air conditioning systems.

[0076] Obviously, the described embodiments are only a part of the embodiments of this application, not all of them. Without conflict, the embodiments and features in the embodiments of this application can be combined with each other. The components of the embodiments of this application described and illustrated herein can generally be arranged and designed in various different configurations. Therefore, the detailed description of the embodiments of this application is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

Claims

1. A subway station air conditioning energy-saving control device based on surveillance video, characterized in that: It includes: A surveillance camera array is used to collect real-time video data on the distribution of people within subway stations; A video signal transmission network that connects to the surveillance camera array to transmit video data; The image processing unit is connected to the video signal transmission network and is used to receive video data and perform image recognition processing. The central control unit, connected to the image processing unit, is used to receive the image recognition processing results from the image processing unit and output control commands. The air supply temperature control device is connected to the central control unit and is used to receive control commands and adjust the air supply temperature of the air conditioning system. Chilled water flow control device, connected to the central control unit, is used to receive control commands and adjust the chilled water flow of the air conditioning system; It also includes an air supply speed adjustment device, which is connected to the central control unit to receive control commands and adjust the air supply speed of the air conditioning system.

2. The energy-saving control device for subway station air conditioning based on surveillance video as described in claim 1, characterized in that: The surveillance camera group includes two or more high-definition cameras, which are distributed and installed in the concourse and platform of the subway station; or the surveillance camera group includes two or more high-definition cameras and at least one infrared thermal imaging camera, which assists in collecting the body surface temperature information of people; the temperature measurement accuracy of the infrared thermal imaging camera is not less than ±0.3℃, and the temperature measurement range is -20℃ to +60℃.

3. The energy-saving control device for subway station air conditioning based on surveillance video as described in claim 1, characterized in that: The image processing unit is configured to perform personnel density recognition and thermal demand recognition on video data; the image processing unit has GPU-accelerated computing capabilities and supports parallel processing of multiple video streams.

4. The energy-saving control device for subway station air conditioning based on surveillance video as described in claim 1, characterized in that: The central control unit has a built-in preset energy-saving strategy, and the central control unit is configured to generate control commands according to the preset energy-saving strategy.

5. A subway station air conditioning energy-saving control device based on surveillance video according to claim 1, characterized in that: The central control unit includes a core processor, which executes control logic and data processing, and outputs control commands; The data storage device is used to store historical data and operating strategies; the input / output interface is used for data communication with various control devices.

6. A subway station air conditioning energy-saving control device based on surveillance video according to claim 1, characterized in that: The air supply temperature control device includes: a temperature sensor for real-time monitoring of the air supply temperature; and a temperature regulation actuator for adjusting the air supply temperature according to control commands, wherein the temperature regulation actuator is an electric valve or a frequency converter.

7. A subway station air conditioning energy-saving control device based on surveillance video according to claim 1, characterized in that: The chilled water flow control device includes: a chilled water pump for providing power for chilled water circulation; an electric regulating valve for adjusting the chilled water flow according to control commands; and a flow sensor, which uses an electromagnetic flow meter or an ultrasonic flow meter with a measurement accuracy of not less than ±1%, for real-time monitoring of chilled water flow and providing feedback signals.

8. A subway station air conditioning energy-saving control device based on surveillance video according to claim 1, characterized in that: The air supply speed adjustment device includes: a variable frequency fan for adjusting the air supply speed; a jet induction fan unit for auxiliary diffusion in densely populated areas of the subway station; and a wind speed sensor, which adopts a thermal wind speed sensor or an ultrasonic wind speed sensor with a measurement range of 0-10m / s and an accuracy of not less than ±3%, for real-time monitoring of the air supply speed.

9. A subway station air conditioning energy-saving control device based on surveillance video according to claim 1, characterized in that: It also includes an environmental parameter monitoring device, which is connected to the central control unit to monitor environmental parameters such as temperature, humidity, CO2 concentration, and PM2.5 concentration in the subway station.

10. A subway station air conditioning energy-saving control device based on surveillance video according to claim 1, characterized in that: The central control unit is also connected to a data communication device, which exchanges data with the subway operation management center.

Images