Self-adaptive energy-saving control method for environment in subway station

Abstract

The invention belongs to the field of subway station environment regulation and control, and discloses a self-adaptive energy-saving control method for the environment in a subway station. Comprising the following steps: calculating an outdoor enthalpy value and an indoor enthalpy value by using an environment parameter set, and performing optimization calculation on indoor environment data by using an improved smoothing algorithm for selecting and controlling an operation mode; predefining an operation mode, and setting a judgment standard of the operation mode; setting an operation mode switching logic and a smooth switching mechanism, and carrying out adaptive adjustment on an operation mode in the station; designing a dynamic association model based on the environmental parameter set, associating and affiliating parameters of the environmental parameter set, designing a parameter gradual change optimization model based on the dynamic association model, outputting optimized control parameters, and performing rolling updating by changing and outputting the control parameters according to a time sequence in an adjusting period. Switching of the operation modes is completed by minimizing the objective function, and self-adaptive energy-saving control over the environment in the subway station is achieved.

Description

Technical Field

[0001] The present invention relates to the field of subway station environment control, and more specifically, to a method for adaptive energy-saving control of the environment in a subway station. Background Art

[0002] With the rapid development of subway transportation, the energy consumption problem of subway station ventilation and air-conditioning systems has become increasingly serious. Traditional ventilation and air-conditioning systems use fixed control modes when in operation. Taking summer as an example, no matter how the outdoor temperature changes, the cooling capacity output is always maintained constant, resulting in a large amount of energy waste; in the transition season, even if the outdoor temperature and humidity are suitable, it will not automatically switch to natural ventilation mode, and it will still consume energy to operate. In addition, there are fewer operating modes, making it difficult to finely control the environment in the station, which leads to resource waste. Due to the large environmental gap in the just-mode, its temperature and humidity control relies on simple thermostats and humidity regulators, with extremely poor accuracy. Indoor temperature fluctuations often exceed ±3℃, and humidity fluctuations exceed ±10%, causing passengers to feel uncomfortable. In addition, in the process of using and adjusting the control parameters, the longer the adjustment step, the more rapid energy consumption will be caused in a short period of time, and the one-step parameter control will also lead to poor adjustment accuracy.

[0003] In view of this, the present invention proposes a method for adaptive energy-saving control of the environment in a subway station to solve the above-mentioned problem. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: a method for adaptive energy-saving control of the environment in a subway station, comprising: step S1: real-time collection of an environmental parameter set;

[0005] Step S2: using the environmental parameter set to calculate the outdoor enthalpy value and the indoor enthalpy value, and using the improved smoothing algorithm to optimize the indoor environmental data for selection and control of the operation mode;

[0006] Step S3: predefine the operation mode, which includes natural ventilation mode, small fresh air mode, refrigeration and dehumidification mode, dehumidification priority mode, carbon dioxide control mode and energy-saving standby mode, and set the judgment criteria of the operation mode; set the operation mode switching logic and smooth switching mechanism, and adaptively adjust the operation mode in the station;

[0007] Step S4: design a dynamic association model based on the environmental parameter set, associate and link the parameters of the environmental parameter set, design a parameter gradient optimization model based on the dynamic association model, output the optimized control parameters, and perform rolling updates by changing the output control parameters according to the time series within the adjustment period, and complete the switching of the operation mode by minimizing the objective function;

[0008] Step S5: Arrange the data acquisition and analysis module, the operation mode design module, and the operation mode control and adjustment module on the visualization interface for interface interaction with the user.

[0009] Preferably, the set of environmental parameters includes outdoor environmental data, indoor environmental data, and system operation status data;

[0010] The outdoor environmental data includes the temperature, relative humidity, wind speed, PM2.5 concentration, and atmospheric pressure outside the station.

[0011] The indoor environmental data includes the temperature, relative humidity, carbon dioxide concentration, and passenger flow on the concourse level and the platform level.

[0012] The system operation status data includes the supply and return water temperatures of the chilled water system of the air conditioner, the water temperature at the outlet of the return cooling tower, the heat exchange temperature of the condenser, the air volume, and the flow rate.

[0013] Preferably, the method for calculating the outdoor enthalpy value and the indoor enthalpy value using the set of environmental parameters includes:

[0014] Define the outdoor enthalpy value as H_out and the indoor enthalpy value as H_in;

[0015] Step A1: Obtain the atmospheric pressure P in the outdoor environmental data. If the atmospheric pressure P ∈ [80 kPa, 110 kPa], it is marked as normal data; otherwise, the data is marked as abnormal. If the data is abnormal, obtain it again and give an alarm;

[0016] Step A2: Calculate the saturated water vapor pressure Ps according to the temperature T in segments. Then when T ≥ 0°C, When T < 0°C,

[0017] Step A3: Calculate the moisture content of the air When it is marked as normal data; otherwise, the data is marked as abnormal;

[0018] Step A4: Calculate the enthalpy value H = 1.006×T + W×(2501 + 1.86×T). Assign T as the temperature T_out in the outdoor environmental data and the temperature T_in in the indoor environmental data respectively, Assign the relative humidity in the outdoor environmental data and the relative humidity in the indoor environmental data respectively.

[0019] If the enthalpy value H ∈ [-10 kJ / kg, 150 kJ / kg], it is marked as normal data; otherwise, the data is marked as abnormal.

[0020] Preferably, the method for optimizing and calculating indoor environment data using an improved smoothing algorithm includes:

[0021] Set a dynamic sliding window where K_min is the predefined minimum sliding window, Cov(J_j, c_co2) represents the covariance between the degree of personnel aggregation J_j and the carbon dioxide concentration c_co2, σ(J_j) is the standard deviation of the degree of personnel aggregation J_j, and σ(c_co2) is the standard deviation of the carbon dioxide concentration c_co2;

[0022] Define the current cycle time, average the values at the same collection point, arrange them in chronological order, perform a moving average on the carbon dioxide concentration in chronological order using the dynamic sliding window, subtract the average from the moving average value, then arrange the average values in order, and take the median as the carbon dioxide concentration in the final indoor environment data;

[0023] Use weighted average to calculate the indoor average temperature T_avg and the average relative humidity And set the weight of the concourse level in the weighted average to 0.7 and the weight of the platform level to 0.3.

[0024] Preferably, the method for setting the judgment criteria for the operating mode includes;

[0025] The judgment criteria for the natural ventilation mode are: the outdoor enthalpy value is lower than the indoor enthalpy value; the temperature T_out in the outdoor environmental data is in the range of 20 to 26 °C, the PM2.5 concentration is less than 50 μg / m3, and the wind speed is greater than 0.5 m / s;

[0026] The judgment criteria for the small fresh air mode are: the outdoor enthalpy value is higher than the indoor enthalpy value; the carbon dioxide concentration is less than 600 ppm;

[0027] The judgment criteria for the refrigeration and dehumidification mode are: the average relative humidity is higher than 65%; the average temperature is in the range of 24 to 26 °C;

[0028] The judgment criteria for the carbon dioxide control mode are: the carbon dioxide concentration is higher than 800 ppm;

[0029] The judgment criteria for the energy-saving standby mode are: the degree of personnel aggregation is lower than the preset standard value.

[0030] Preferably, the method for setting the operating mode switching logic and the smooth switching mechanism and adaptively adjusting the mode running in the station includes:

[0031] Define the priority order of the modes from high to low as: natural ventilation mode, small fresh air mode, refrigeration and dehumidification mode, dehumidification priority mode, carbon dioxide control mode, energy-saving standby mode;

[0032] Identify the current operating mode and mode lock time, and set scoring thresholds and cost thresholds;

[0033] Calculate real-time score If the real-time score is greater than the score threshold and the current operating mode is not the natural ventilation mode, it will switch to the natural ventilation mode. If the conditions of the current operating mode are no longer met and the downgrade conditions are met, it will downgrade to a mode with a lower priority.

[0034] in, and is the weight coefficient, V_wind is the wind speed, c_PM2.5 is the PM2.5 concentration;

[0035] Preset the lock time and hysteresis conditions of the mode, and switch through conditional triggers;

[0036] Calculate the mode switching cost Cs = γ1×ΔE+γ2×ΔC. If the switching cost Cs is greater than the cost threshold, γ1 and γ2 are weight coefficients, ΔE is the energy consumption change caused by mode switching, and ΔC is the comfort change.

[0037] Preferably, the method of designing a dynamic association model based on an environmental parameter set and associating and linking the parameters of the environmental parameter set includes:

[0038] The dynamic correlation model is formed by horizontal splicing of the chilled water system model, indoor temperature change model, indoor dehumidification model and carbon dioxide concentration model;

[0039] The output of the chilled water system model is cooling capacity, so cooling capacity Qc = δ × c p ×mw×(T g -T h ), where δ is the density of water, c p is the specific heat capacity of water, mw is the flow rate of the system operation status data, T g and T h They are respectively the supply and return water temperatures in the system operation status data;

[0040] The dynamic equation of the indoor temperature variation model is: in, is the density of air, is the specific heat capacity of air, V in is the indoor volume of the station, ΔT in_b is the unit change of indoor temperature, Qlozd is the indoor heat load, and ma is the air volume in the system operation status data;

[0041] The dynamic equation of the indoor dehumidification model is: Where, ΔWin_b is the unit change of indoor relative humidity, M de is the dehumidification capacity;

[0042] The dynamic equation of the carbon dioxide concentration model is V in ×ΔCO 2_in_b = c_co2 - ma×(k_in(CO2) - S_out(CO2)), where k_in(CO2) is the amount of carbon dioxide generated by the passenger flow, S_out(CO2) is the outdoor carbon dioxide concentration, and ΔCO 2_in_b is the unit change of indoor carbon dioxide concentration.

[0043] Preferably, the parameter gradient optimization model is designed based on the dynamic association model, and the optimized control parameters are output. The control parameters are output in sequence according to the time series within the adjustment period for rolling update, and the operation mode is switched by minimizing the objective function. The method includes:

[0044] Set the objective function of the parameter gradient optimization model as where ∈1, ∈2, ∈3, and ∈4 are predefined weight coefficients. When the dynamic association model outputs the control parameters for the kth time during the adjustment time, E(k) is the energy consumption of the air conditioner when adjusting with the control parameters, is the difference between the indoor relative humidity and the target relative humidity when adjusting with the control parameters, co2(k) is the difference between the indoor carbon dioxide concentration and the target carbon dioxide concentration when adjusting with the control parameters, and T(k) is the difference between the indoor temperature and the target temperature when adjusting with the control parameters;

[0045] Set the constraint condition as that the control parameters output by the dynamic association model for the kth time during the adjustment time are all within the numerical range specified by the operation mode;

[0046] By minimizing the objective function within the adjustment period time, when the objective function is minimized, the operation mode switching is completed, and then the switched operation mode is used for the environmental control in the station.

[0047] Preferably, the use of the control parameters includes:

[0048] Step D1: Obtain the control parameters output by the dynamic association model for the kth time during the adjustment time;

[0049] Step D2: Use PID control to arrange the control parameters on the air conditioner and use the parameter gradient optimization model to optimize the control parameters;

[0050] Step D3: Repeat Step D1 and Step D2 until the adjustment time is consumed or the objective function is minimized, and then stop to complete the operation mode switching;

[0051] Step D4: Use the switched operation mode to control the environment in the station.

[0052] Preferably, the visual interface includes a terminal page of a computer or a display interface of a mobile device.

[0053] The technical effects and advantages of the adaptive energy-saving control method for the environment in a subway station of the present invention are as follows:

[0054] 1. Energy saving and high efficiency

[0055] Through adaptive operation mode selection, natural ventilation mode and small fresh air mode are given priority to reduce the operation time of the air conditioning system and reduce energy consumption. The dynamic association model and parameter gradient optimization model comprehensively consider multi-objective optimization such as energy consumption, temperature, humidity and carbon dioxide concentration to ensure that the system meets comfort requirements while saving energy. The smooth switching mechanism avoids frequent mode switching, reducing equipment loss and energy consumption fluctuations.

[0056] 2. Strong environmental adaptability

[0057] The system can dynamically adjust the operation mode according to changes in the outdoor environment (such as temperature, humidity, PM2.5 concentration) and indoor environment (such as passenger flow, carbon dioxide concentration) to adapt to different climate conditions and passenger flow peaks. The improved smoothing algorithm and enthalpy calculation method improve the accuracy and reliability of environmental parameters, providing a scientific basis for mode selection.

[0058] 3. Comfort and health are taken into consideration

[0059] Through the CO2 control mode and dehumidification priority mode, the indoor air quality and humidity are adjusted in time to ensure the health and comfort of passengers. The weighted average calculation of indoor temperature and humidity (the weight of the concourse layer is 0.7, and the weight of the platform layer is 0.3) is more in line with the actual usage scenario and optimizes the passenger experience.

[0060] 4. High degree of intelligence and automation

[0061] The system achieves automatic control through dynamic association models and parameter gradient optimization models, reduces manual intervention, and improves operating efficiency. The mode switching logic and scoring mechanism are highly intelligent and can automatically adjust the operating mode according to real-time scores and cost thresholds.

[0062] 5. System stability and reliability

[0063] Data anomaly detection (such as abnormal enthalpy value and abnormal atmospheric pressure) ensures the reliability of input data and avoids control errors caused by data errors. The smooth switching mechanism and mode lock time design reduce the instability of system operation and extend the service life of the equipment.

[0064] This solution realizes intelligent control and energy-saving optimization of the environment in subway stations through accurate collection and optimization of environmental parameters, intelligent selection and adaptive adjustment of operation modes, dynamic correlation model and parameter gradient optimization, and visual interface design. Its technical effects are reflected in the accuracy of environmental monitoring, intelligent operation mode, optimization of control parameters and significant improvement of energy-saving effects; its advantages include energy-saving and high efficiency, strong environmental adaptability, both comfort and health, high degree of intelligence, good system stability, strong scalability and high comprehensive cost-effectiveness. This solution has high application value in the field of subway station environmental control, and can effectively improve the station's operating efficiency and passenger experience, while achieving the goal of energy conservation and emission reduction. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a structural schematic diagram of a method for adaptive energy-saving control of the environment in a subway station according to the present invention;

[0066] Figure 2 The figure is a schematic diagram of the steps of a method for adaptive energy-saving control of the environment in a subway station according to the present invention. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] Example 1

[0069] See also Figure 1 and Figure 2 As shown, the method for adaptive energy-saving control of the environment in a subway station described in this embodiment includes:

[0070] With the rapid development of subway transportation, the energy consumption problem of subway station ventilation and air conditioning systems has become increasingly severe. When the traditional ventilation and air conditioning system operates, it adopts a fixed control mode. Taking summer as an example, regardless of how the outdoor temperature changes, it always maintains a constant cooling capacity output, resulting in a large amount of energy waste; in the transitional season, even if the outdoor temperature and humidity are suitable, it will not automatically switch to the natural ventilation mode and still operates energy-consuming. Its temperature and humidity control relies on simple thermostats and humidity regulators, with extremely poor accuracy. The indoor temperature fluctuation often exceeds ±3°C, and the humidity fluctuation exceeds ±10%, causing discomfort to passengers. In contrast, the present invention aims to break these limitations and achieve the perfect integration of high energy efficiency and precise comfort through an innovative energy-saving control method. The daily average energy consumption of the station air conditioning system (including the large system and water system equipment) of the system of the present invention is 1000 kWh (operating time of 17 hours), saving more than 50% of energy per day compared with the traditional control system.

[0071] Data acquisition and analysis module: used to collect the environmental parameter set in real time, calculate the outdoor enthalpy value and the indoor enthalpy value using the environmental parameter set, and perform optimized calculation on the indoor environmental data using the improved smoothing algorithm for the selection and control of the operating mode;

[0072] Step S1: Collect the environmental parameter set in real time;

[0073] Step S2: Calculate the outdoor enthalpy value, the indoor enthalpy value, the carbon dioxide concentration, and the temperature and humidity in the indoor environmental data;

[0074] The environmental parameter set includes outdoor environmental data, indoor environmental data, and system operating status data;

[0075] The outdoor environmental data includes the temperature, relative humidity, wind speed, PM2.5 concentration, and atmospheric pressure outside the station;

[0076] The indoor environmental data includes the temperature, relative humidity, carbon dioxide concentration, and passenger flow on the concourse level and the platform level.

[0077] The system operating status data includes the supply and return water temperatures of the chilled water system of the air conditioner, the outlet water temperature of the return cooling tower, the condenser heat exchange temperature, the air volume, and the flow rate.

[0078] Arrange sensors at the locations where the environmental data is collected. For example, evenly lay 10 temperature sensors outside each station, and so on. By arranging sensors at the places required for data collection and having the sensors collect the corresponding values, the accuracy of the sensors is required to be within a certain range. For example, temperature: ±0.1°C; humidity: ±2%RH; carbon dioxide concentration: ±50 ppm; other parameters: meet the industrial-grade accuracy requirements.

[0079] The method for calculating the outdoor enthalpy value and the indoor enthalpy value using the environmental parameter set includes:

[0080] Define the outdoor enthalpy value as H_out and the indoor enthalpy value as H_in; the enthalpy value is used to determine whether the outdoor air is suitable for natural ventilation.

[0081] Step A1: Obtain the atmospheric pressure P in the outdoor environmental data. If the atmospheric pressure P ∈ [80 kPa, 110 kPa], it is marked as normal data; otherwise, the data is marked as abnormal. If the data is abnormal, obtain it again and give an alarm.

[0082] Step A2: Calculate the saturated water vapor pressure Ps in segments according to the temperature T. Then when T ≥ 0°C, When T < 0°C,

[0083] Step A3: Calculate the moisture content of the air When If so, it is marked as normal data; otherwise, the data is marked as abnormal, indicating that the atmospheric pressure P, the saturated water vapor pressure Ps, and the relative humidity are abnormal. If the sensor reading is incorrect, obtain it again and trigger an alarm. For example, the alarm prompt is: "The humidity data is abnormal, Please check the sensor data." The purpose is to ensure that W ≥ 0, otherwise the data is marked as abnormal.

[0084] Step A4: Calculate the enthalpy value H = 1.006×T + W×(2501 + 1.86×T). Assign T to the temperature T_out in the outdoor environmental data and the temperature T_in in the indoor environmental data respectively. Assign the relative humidity in the outdoor environmental data and the relative humidity in the indoor environmental data respectively. Then the obtained enthalpy value H is the outdoor enthalpy value H_out and the indoor enthalpy value H_in.

[0085] If the enthalpy value H ∈ [-10 kJ / kg, 150 kJ / kg], it is marked as normal data; otherwise, the data is marked as abnormal.

[0086] Among them, the humidity sensor is the most direct and common method to obtain the relative humidity. The relative humidity can also be obtained through meteorological data.

[0087] When using the enthalpy value to judge whether a station is ventilated, due to the natural influence of air pressure inside and outside the station, the air pressure difference will affect the effect of ventilation and air change. If only relying on temperature for enthalpy value judgment and ignoring the influence of air pressure, errors are likely to occur in the selection of operating modes, resulting in inaccurate judgment. Therefore, the real-time measured atmospheric pressure is introduced to improve the accuracy of enthalpy value calculation. In addition, when the sensor collects data, there will be incorrect data. Since there are a large number of sensors arranged in the station and real-time performance is required for mode selection and switching, a huge amount of data will be generated during continuous supervision by the sensors. If the data is judged for anomalies individually, it will increase the occupancy of data operation memory, reduce the operation efficiency, and generally the network speed of the station's networking is slow. Therefore, the occupancy of excessive data memory will drag down the operation of other modules and affect the overall operation efficiency. Therefore, judgment is made after data calculation, comprehensively considering the usage effect of data, and magnifying the associated influence between data, which will greatly reduce the computing power of data processing and improve the data processing effect. In addition, rationality verification of the data is carried out, data anomalies are marked and alarms are given, which improves the timely processing ability and forms logs for easy reference.

[0088] The method for optimizing and calculating indoor environmental data using an improved smoothing algorithm includes:

[0089] Since people are prone to gather in the station, resulting in uneven distribution of personnel, and thus the higher the degree of crowd gathering, the faster the carbon dioxide concentration rises and the higher it becomes in the place where people gather more, while in the place where there are fewer people, the carbon dioxide concentration is lower. And the sensors are evenly distributed, which will cause fluctuations in single-point data, resulting in the final output carbon dioxide concentration value not being representative and difficult to represent the overall situation of carbon dioxide concentration in the station. Based on this, a smoothing algorithm is used for its optimization calculation. The specific method is as follows:

[0090] Set a dynamic sliding window Among them, K_min is the predefined minimum sliding window, represents the covariance between the degree of personnel gathering J_j and the carbon dioxide concentration c_co2, σ(J_j) is the standard deviation of the degree of personnel gathering J_j, and σ(c_co2) is the standard deviation of the carbon dioxide concentration c_co2;

[0091] The degree of personnel gathering J_j can obtain the number of people in different areas of the station through a sensor network or a video monitoring system. For example, using a thermal imaging camera or a Wi-Fi signal-based people counting system. The carbon dioxide concentration c_co2 here can be the historical data in the previous cycle. For example, if the sliding window is adjusted every 3 minutes, then in the current cycle, the carbon dioxide concentration c_co2 here is the value after optimization calculation of the historical data in the previous 3-minute cycle.

[0092] Define the current cycle time. After averaging the values at the same collection point and arranging them in chronological order, use a dynamic sliding window to perform a moving average on the carbon dioxide concentration in chronological order. Subtract the average value from the moving average value, then arrange the average values in order and take the median as the carbon dioxide concentration in the final indoor environment data;

[0093] Among them, from a time perspective, the data collected within a 3-minute cycle can be regarded as being horizontally expanded in a time series. That is to say, each collection point has a value at each time point. First, arrange the values at each collection point in chronological order, use a dynamic sliding window for processing, obtain the processed data of each collection point within the cycle time, then perform an average processing on these data to calculate the average value, and get the representative value of each sampling point within the cycle time. Each sampling point has a representative carbon dioxide concentration, and this carbon dioxide concentration is related to the degree of crowd gathering. Then take the median. Compared with the average value, the median better represents the main carbon dioxide concentration at each sampling point in the station. Here, the sampling point is the location where the sensor is arranged, that is, the place where data is collected using the sensor.

[0094] Use weighted average to calculate the indoor average temperature T_avg and average relative humidity And set the weight of the concourse level to 0.7 and the weight of the platform level to 0.3 in the weighted average;

[0095] The specific calculation formula can be ω can be used to represent the weights of the concourse level and the platform level.

[0096] Operation mode design module: Used to predefined operation modes, including natural ventilation mode, small fresh air mode, cooling and dehumidification mode, dehumidification priority mode, carbon dioxide control mode, and energy-saving standby mode, and set the judgment criteria for the operation modes; Set the operation mode switching logic and smooth switching mechanism, and adaptively adjust the mode running in the station;

[0097] Set the judgment criteria for the operation modes, and the methods include;

[0098] The judgment criteria for the natural ventilation mode are: the outdoor enthalpy value is lower than the indoor enthalpy value; the temperature T_out in the outdoor environmental data is in the range of 20 to 26 °C, the outdoor temperature is in the appropriate range, the PM2.5 concentration is less than 50 μg / m 3 , the air quality is good, and the wind speed is greater than 0.5 m / s; the wind speed is appropriate; the control target is to stop refrigeration and use natural wind to cool down.

[0099] The judgment criteria for the small fresh air mode are: the outdoor enthalpy value is higher than the indoor enthalpy value; the air quality requirement is low, and the carbon dioxide concentration is less than 600 ppm; the control target is to reduce the fresh air ratio and reduce the refrigeration load.

[0100] The judgment criteria for the refrigeration and dehumidification mode are as follows: the average relative humidity is higher than 65%; the average relative humidity is too high, but the average temperature is within the appropriate range, and the average temperature is in the range of 24 to 26 °C; the control objective is to dehumidify first and avoid excessive refrigeration.

[0101] The judgment criteria for the carbon dioxide control mode are as follows: the carbon dioxide concentration is higher than 800 ppm; the carbon dioxide concentration exceeds the standard, and the control objective is to increase the fresh air volume and reduce the carbon dioxide concentration.

[0102] The judgment criteria for the energy-saving standby mode are as follows: the degree of personnel aggregation is lower than the preset standard value; at the end of operation or during off-peak hours, the environmental load is low, and the control objective is to reduce the operating frequency and maintain the minimum environmental requirements. The standard value can be set independently by the management staff, for example, 3.

[0103] Analysis of the application scenarios of the operation mode. For example, in different seasons, in summer with high temperature and high humidity, the refrigeration and dehumidification mode is selected for the operation mode. In winter with low temperature and dryness, the energy-saving standby mode is selected for the operation mode. In the transitional season, the natural ventilation mode is selected for the operation mode. Also, for example, the operation plans for different passenger flow periods. During peak hours, the carbon dioxide control mode is the operation mode. The fresh air volume is increased preferentially, and at the same time, according to the temperature and humidity conditions, the refrigeration and dehumidification mode or the small fresh air mode is dynamically switched. During off-peak hours, the passenger density is low and the environmental load is small. The operation mode is the energy-saving standby mode, reducing the operating frequency of the air-conditioning equipment and maintaining the minimum fresh air volume and temperature and humidity control. After the operation is over and there are no passengers, only the basic state of the equipment and the station environment needs to be maintained. The operation mode is the energy-saving standby mode, turning off most of the equipment and only retaining the monitoring system and necessary fresh air supplement.

[0104] Set the operation mode switching logic and smooth switching mechanism, and perform adaptive adjustment on the mode running in the station. The methods include:

[0105] Define the priority order of the modes from high to low as: natural ventilation mode, small fresh air mode, refrigeration and dehumidification mode, dehumidification priority mode, carbon dioxide control mode, energy-saving standby mode;

[0106] Identify the current operation mode and the mode locking time, and set the scoring threshold and cost threshold;

[0107] Calculate the real-time score If the real-time score is greater than the scoring threshold and the current operation mode is not the natural ventilation mode, then switch to the natural ventilation mode. If the conditions of the current operation mode are no longer met, that is, the real-time score is less than or equal to the scoring threshold and the downgrading conditions are met, then downgrade to a mode with a lower priority.

[0108] Among them, and is the weight coefficient, which can be adjusted according to actual needs, for example and V_wind is wind speed, c_PM2.5 is PM2.5 concentration;

[0109] The upgrade condition is that if the applicable conditions of the upper mode are met, the mode is switched to a higher priority mode. The downgrade condition is that if the conditions of the current mode are no longer met, the mode is downgraded to a lower priority mode.

[0110] Preset the lock time of the mode (e.g. 5 minutes, 3 minutes, etc., to avoid frequent mode switching) and hysteresis conditions (e.g. temperature difference greater than 1 degree Celsius or carbon dioxide concentration greater than 800ppm), and switch through conditional triggers (e.g. temperature difference greater than 1 degree Celsius for more than 2 minutes or carbon dioxide concentration greater than 800ppm for more than 3 minutes);

[0111] Calculate the mode switching cost Cs = γ1 × ΔE + γ2 × ΔC. If the switching cost Cs is greater than the cost threshold, suspend the switching to avoid equipment wear and energy consumption fluctuations caused by frequent switching. γ1 and γ2 are weight coefficients, which are adjusted according to energy saving priority or comfort priority. ΔE is the energy consumption change caused by mode switching (unit: kWh). ΔC is the comfort change (for example, the weighted sum of temperature and humidity deviations);

[0112] Operation mode control and adjustment module: Design a dynamic association model based on the environmental parameter set, associate and link the parameters of the environmental parameter set, design a parameter gradient optimization model based on the dynamic association model, output the optimized control parameters, and perform rolling updates by changing the output control parameters according to the time series within the adjustment period, and complete the switching of the operation mode by minimizing the objective function;

[0113] The dynamic behavior of ventilation and air conditioning systems can be described by thermodynamic and fluid dynamic models, covering key parameters such as chilled water systems, cooling towers, condensers, air volume and flow, as well as the relationship between indoor environment temperature, relative humidity, carbon dioxide concentration and passenger flow. The goal of the dynamic model is to predict the energy consumption and comfort of the system under different parameters.

[0114] Design a dynamic association model based on the environment parameter set to associate the parameters of the environment parameter set. The method includes:

[0115] The dynamic correlation model is formed by horizontal splicing of the chilled water system model, indoor temperature change model, indoor dehumidification model and carbon dioxide concentration model;

[0116] The output of the chilled water system model is the cooling capacity. The cooling capacity of the chilled water system is related to the supply and return water temperature difference and flow rate. The cooling capacity Qc = δ × c p ×mw×(T g-T h ), where δ is the density of water, c p is the specific heat capacity of water, mw is the flow rate of the system operating state data, i.e., the chilled water mass flow rate, T g and T h are the supply and return water temperatures in the system operating state data, i.e., the chilled water supply temperature and return water temperature, respectively;

[0117] The change in indoor temperature is related to the cooling capacity input, air volume, and indoor heat load. Then, the dynamic equation of the indoor temperature change amount model is where is the density of air, is the specific heat capacity of air, V in is the indoor volume in the station, ΔT in_b is the unit change amount of indoor temperature, Qlozd is the indoor heat load, and the indoor heat load can be obtained through the heat balance method, heat index method, or empirical formula method. ma is the air volume in the system operating state data, i.e., the supply air mass flow rate;

[0118] The change in indoor relative humidity RH is related to the dehumidification amount and fresh air volume. Then, the dynamic equation of the indoor dehumidification amount model is where ΔW in_b is the unit change amount of indoor relative humidity, M de is the dehumidification amount;

[0119] The change in carbon dioxide concentration is related to the fresh air volume and passenger flow. Then, the dynamic equation of the carbon dioxide concentration model is where k_in(CO2) is the amount of carbon dioxide generated by passenger flow, S_out(CO2) is the outdoor carbon dioxide concentration, and ΔCO 2_in_b is the unit change amount of indoor carbon dioxide concentration.

[0120] The dynamic model of the ventilation and air conditioning system covers the mutual relationships of the chilled water system, indoor temperature, humidity, and carbon dioxide concentration. Through these models, the energy consumption and comfort of the system under different parameters can be predicted, providing a theoretical basis for optimal control.

[0121] Based on the dynamic correlation model, a parameter gradual change optimization model is designed to output the optimized control parameters. The control parameters are output in sequence according to the time series within the adjustment period for rolling update, and the operation mode is switched by minimizing the objective function. The methods include:

[0122] Set the objective function of the parameter gradual change optimization model as Among them, ∈1, ∈2, ∈3, and ∈4 are predefined weight coefficients, that is, they are preset by managers. When the dynamic association model outputs control parameters for the kth time within the adjustment time, E(k) is the energy consumption of the air conditioner when adjusting with the control parameters. is the difference between the indoor relative humidity and the target relative humidity when adjusting with the control parameters, co2(k) is the difference between the indoor carbon dioxide concentration and the target carbon dioxide concentration when adjusting with the control parameters, and T(k) is the difference between the indoor temperature and the target temperature when adjusting with the control parameters; the target relative humidity refers to the value of the relative humidity under the selected operating mode, and the target carbon dioxide concentration and target temperature are similar.

[0123] Set the constraint condition that the control parameters output by the dynamic association model for the kth time within the adjustment time are all within the numerical range specified by the operating mode.

[0124] By minimizing the objective function within the adjustment cycle time, when the objective function is minimized, the operating mode switching is completed, and then the switched operating mode is used for the environmental control in the station.

[0125] The use of control parameters includes:

[0126] Step D1: Obtain the control parameters output by the dynamic association model for the kth time within the adjustment time.

[0127] Step D2: Use PID control to arrange the control parameters on the air conditioner and use the parameter gradient optimization model to optimize the control parameters.

[0128] Step D3: Repeat Step D1 and Step D2 until the adjustment time is consumed or the objective function is minimized and then stop, completing the switching of the operating mode.

[0129] Step D4: Use the switched operating mode to control the environment in the station.

[0130] Visualization module: Arrange the data acquisition and analysis module, operating mode design module, operating mode control and adjustment module on the visualization interface for interface interaction with users.

[0131] The visualization interface includes the end page of a computer or the display interface of a mobile device.

[0132] Users can perform interactive operations such as clicking, querying, downloading, or numerical setting on the entire adjustment through the computer end page (computer display screen, here the computer refers to an intelligent device, and the mobile device can be a mobile phone or a tablet).

[0133] Embodiment 2

[0134] Please refer to Figure 1As shown, the part not described in detail in this embodiment is described in Example 1, which provides an adaptive energy-saving control system for the environment in a subway station, including:

[0135] Data acquisition and analysis module: used to collect environmental parameter sets in real time, use the environmental parameter sets to calculate outdoor enthalpy values and indoor enthalpy values, and use improved smoothing algorithms to optimize the calculation of indoor environmental data for the selection and control of operation modes;

[0136] Operation mode design module: used to predefine the operation mode, including natural ventilation mode, small fresh air mode, refrigeration and dehumidification mode, dehumidification priority mode, carbon dioxide control mode and energy-saving standby mode, and set the judgment criteria of the operation mode; set the operation mode switching logic and smooth switching mechanism, and make adaptive adjustments to the operation mode in the station;

[0137] Operation mode control and adjustment module: Design a dynamic association model based on the environmental parameter set, associate and link the parameters of the environmental parameter set, design a parameter gradient optimization model based on the dynamic association model, output the optimized control parameters, and perform rolling updates by changing the output control parameters according to the time series within the adjustment period, and complete the switching of the operation mode by minimizing the objective function;

[0138] Visualization module: Arrange the data acquisition and analysis module, operation mode design module, operation mode control and adjustment module on the visualization interface to interact with the user.

[0139] By collecting outdoor environmental data (temperature, humidity, wind speed, PM2.5 concentration, atmospheric pressure), indoor environmental data (temperature, humidity, carbon dioxide concentration, passenger flow) and system operation status data (chilled water supply and return water temperature, air volume, etc.) in real time, we can fully grasp the environmental conditions inside and outside the station.

[0140] An improved smoothing algorithm is used to optimize the processing of indoor environmental data (such as dynamic sliding window processing of carbon dioxide concentration, weighted average calculation of temperature and humidity), effectively reducing data noise, improving data reliability, and providing an accurate basis for subsequent operation mode selection and control.

[0141] By calculating the saturated water vapor pressure and air humidity content in sections, the outdoor and indoor enthalpy values are accurately calculated, and abnormal data are marked and warned to ensure the accuracy and stability of the calculation results.

[0142] The natural ventilation mode, small fresh air mode, cooling and dehumidification mode, dehumidification priority mode, carbon dioxide control mode and energy-saving standby mode are predefined, and clear judgment criteria are set (such as enabling the natural ventilation mode when the outdoor enthalpy value is lower than the indoor enthalpy value).

[0143] Through the priority order, scoring threshold, and cost threshold, combined with the pattern lock time and hysteresis conditions, smooth switching of the operating mode is achieved, avoiding increased energy consumption and equipment wear caused by frequent switching.

[0144] According to the changes in real-time environmental parameters, the operating mode is dynamically adjusted to ensure that the system always operates in the optimal mode under different passenger flows, climate conditions, and indoor environmental states.

[0145] Through the dynamic correlation of the chilled water system model, indoor temperature change model, indoor dehumidification model, and carbon dioxide concentration model, the physical change laws of the indoor environment in the station are comprehensively reflected.

[0146] Based on the dynamically correlated model, a parameter gradual optimization model is designed. By minimizing the objective function (comprehensively considering energy consumption, temperature deviation, humidity deviation, and carbon dioxide concentration deviation), the optimized control parameters are output to achieve the balance between energy consumption and comfort. The control parameters are output in sequence according to the time series within the adjustment period to dynamically adjust the operating state of the air conditioner, ensuring the stability and efficiency of the system operation.

[0147] Through PID control and the parameter gradual optimization model, the optimized control parameters are applied to the air conditioning system to achieve smooth switching of the operating mode. The mode switching is completed when the objective function is minimized, and low-energy consumption modes such as natural ventilation mode are preferentially selected to reduce the operating time and energy consumption of the air conditioning system while meeting the indoor comfort requirements.

[0148] The data acquisition and analysis module, operating mode design module, operating mode control and regulation module are integrated into the visualization interface, facilitating users to monitor the station environment status, operating mode, and control parameters in real time. Users can adjust parameters and view the operating status through the interface, improving the operability and transparency of the system.

[0149] Embodiment 3

[0150] This embodiment publicly provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it realizes the operation mode of the above-provided method for adaptive energy-saving control of the indoor environment in a subway station.

[0151] Since the electronic device introduced in this embodiment is the electronic device used to implement an in - subway - station environment adaptive energy - saving control method in the embodiments of the present application, based on the in - subway - station environment adaptive energy - saving control method introduced in the embodiments of the present application, those skilled in the art can understand the specific implementation manners and various forms of variation of the electronic device in this embodiment. Therefore, the specific implementation of how this electronic device implements the method in the embodiments of the present application will not be described in detail here. As long as those skilled in the art implement the electronic device used in an in - subway - station environment adaptive energy - saving control method in the embodiments of the present application, it falls within the scope of protection of the present application.

[0152] The above - mentioned formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain a formula that is closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0153] The above - mentioned are only the preferred embodiments of the present invention. The protection scope of the present invention is not limited to the above - mentioned embodiments. All technical solutions within the idea of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in the technical field, several improvements and refinements made without departing from the principle of the present invention should also be regarded as within the protection scope of the present invention.

Claims

1. An adaptive energy-saving control method for the internal environment of a subway station, characterized in that, include: Step S1: real-time collection of environmental parameter sets; Step S2: using the environmental parameter set to calculate the outdoor enthalpy value and the indoor enthalpy value, and using the improved smoothing algorithm to optimize the indoor environmental data for selection and control of the operation mode; Step S3: predefine the operation mode, which includes natural ventilation mode, small fresh air mode, refrigeration and dehumidification mode, dehumidification priority mode, carbon dioxide control mode and energy-saving standby mode, and set the judgment criteria of the operation mode; set the operation mode switching logic and smooth switching mechanism, and adaptively adjust the operation mode in the station; Step S4: design a dynamic association model based on the environmental parameter set, associate and link the parameters of the environmental parameter set, design a parameter gradient optimization model based on the dynamic association model, output the optimized control parameters, and perform rolling updates by changing the output control parameters according to the time series within the adjustment period, and complete the switching of the operation mode by minimizing the objective function; Step S5: Arrange the data acquisition and analysis module, the operation mode design module, and the operation mode control and adjustment module on the visual interface to interact with the user.

2. The environmental adaptive energy-saving control method in a subway station according to claim 1, characterized in that, The environmental parameter set includes outdoor environmental data, indoor environmental data and system operation status data; Outdoor environmental data include temperature, relative humidity, wind speed, PM2.5 concentration and atmospheric pressure outside the station; Indoor environmental data include temperature, relative humidity, carbon dioxide concentration and passenger flow at the concourse and platform levels. The system operation status data includes the supply and return water temperature of the air-conditioning chilled water system, the return water temperature at the cooling tower outlet, the condenser heat exchange temperature, the air volume and flow rate.

3. The method for adaptively energy-saving control of the internal environment in a subway station according to claim 2, wherein, The method for calculating outdoor enthalpy value and indoor enthalpy value using the environmental parameter set includes: Define the outdoor enthalpy as H_out and the indoor enthalpy as H_in; Step A1: Obtain the atmospheric pressure P in the outdoor environment data. If the atmospheric pressure P∈[80kPa, 110kPa], mark it as normal data. Otherwise, mark the data as abnormal. If the data is abnormal, re-acquire it and issue an alarm. Step A2: Calculate the saturated water vapor pressure Ps in segments according to the temperature T. Then, when T ≥ 0°C, when T < 0°C, Step A3: Calculate the moisture content of the air When it is, then mark it as normal data, otherwise, mark the data as abnormal; Step A4: Calculate the enthalpy value H = 1.006×T + W×(2501 + 1.86×T), and assign T the temperature T_out in the outdoor environmental data and the temperature T_in in the indoor environmental data respectively. Assign the relative humidity in the outdoor environmental data respectively. The relative humidity in the indoor environmental data. Then the obtained enthalpy values H are the outdoor enthalpy value H_out and the indoor enthalpy value H_in. If the enthalpy value H∈[-10kJ / kg, 150kJ / kg], it is marked as normal data, otherwise, the data is marked as abnormal.

4. The adaptive energy-saving control method for the internal environment in a subway station according to claim 3, wherein, The method for optimizing the calculation of indoor environment data using the improved smoothing algorithm comprises: Set a dynamic sliding window Among them, K_min is the predefined minimum sliding window, Cov(J_j, c_co2) represents the covariance between the personnel aggregation degree J_j and the carbon dioxide concentration c_co2, σ(J_j) is the standard deviation of the personnel aggregation degree J_j, and σ(c_co2) is the standard deviation of the carbon dioxide concentration c_co2; Define the current cycle time, average the values at the same collection point, arrange them in chronological order, use a dynamic sliding window to perform sliding average on the carbon dioxide concentration in chronological order, remove the average of the sliding averaged values, and then arrange the averages in order, taking the median as the final carbon dioxide concentration in the indoor environment data; Calculate the indoor average temperature T_avg and average relative humidity using weighted average And set the weight of the concourse level in the weighted average to 0.7 and the weight of the platform level to 0.

3.

5. A method for adaptively controlling energy saving in the environment of a subway station according to claim 4, characterized in that, The judgment criteria for setting the operation mode and the method include: The judgment criteria for the natural ventilation mode are: the outdoor enthalpy value is lower than the indoor enthalpy value; the temperature T_out in the outdoor environment data is between 20 and 26°C, the PM2.5 concentration is less than 50μg / m3, and the wind speed is greater than 0.5m / s; The criteria for the small fresh air mode are: the outdoor enthalpy value is higher than the indoor enthalpy value; the carbon dioxide concentration is less than 600ppm; The criteria for cooling and dehumidification mode are: average relative humidity higher than 65%; average temperature between 24 and 26°C; The criteria for the CO2 control mode are: CO2 concentration is higher than 800ppm; The judgment standard for energy-saving standby mode is: the degree of gathering of people is lower than the preset standard value.

6. The environmental adaptive energy-saving control method in a subway station according to claim 5, wherein, The method of setting the operation mode switching logic and smooth switching mechanism and adaptively adjusting the operation mode in the station includes: The priority order of the defined modes is from high to low: natural ventilation mode, small fresh air mode, cooling and dehumidification mode, dehumidification priority mode, carbon dioxide control mode, and energy-saving standby mode; Identify the current operating mode and mode lock time, and set scoring thresholds and cost thresholds; Calculate real-time score If the real-time score is greater than the score threshold and the current operating mode is not the natural ventilation mode, then switch to the natural ventilation mode. If the conditions of the current operating mode are no longer met and the downgrade conditions are satisfied, then downgrade to a mode with a lower priority. Among them, and are weight coefficients, V_wind is the wind speed, and c_PM2.5 is the PM2.5 concentration; Preset the lock time and hysteresis conditions of the mode, and switch through conditional triggers; Calculate the mode switching cost Cs = γ1×ΔE+γ2×ΔC. If the switching cost Cs is greater than the cost threshold, γ1 and γ2 are weight coefficients, ΔE is the energy consumption change caused by mode switching, and ΔC is the comfort change.

7. A method for self-adaptive energy-saving control of the internal environment in a subway station according to claim 6, characterized in that The method of designing a dynamic association model based on the environment parameter set and associating and linking the parameters of the environment parameter set includes: The dynamic correlation model is formed by horizontal splicing of the chilled water system model, indoor temperature change model, indoor dehumidification model and carbon dioxide concentration model; The output of the chilled water system model is cooling capacity, and the cooling capacity Qc = δ × c p × mw × (T g - T h ), where δ is the density of water, c p is the specific heat capacity of water, mw is the flow rate of the system operation status data, T g and T h are the supply and return water temperatures in the system operation status data respectively; The dynamic equation of the indoor temperature change amount model is Among them, is the density of air, is the specific heat capacity of air, V in is the indoor volume in the station, ΔT in_b is the unit change amount of indoor temperature, Qlozd is the indoor heat load, and ma is the air volume in the system operation status data; The dynamic equation of the indoor dehumidification amount model is where ΔW in_b is the unit change amount of the indoor relative humidity, and M de is the dehumidification amount; The dynamic equation of the carbon dioxide concentration model is V in ×ΔCO 2_in_b = c_co2 - ma×(k_in(CO2) - S_out(CO2)), where k_in(CO2) is the amount of carbon dioxide generated by the passenger flow, S_out(CO2) is the outdoor carbon dioxide concentration, and ΔCO 2_in_b is the unit change of the indoor carbon dioxide concentration.

8. A method for adaptively controlling energy saving in the environment of a subway station according to claim 7, characterized in that, The method of designing a parameter gradient optimization model based on a dynamic association model, outputting optimized control parameters, performing rolling updates by changing the output control parameters according to a time series within an adjustment period, and completing the switching of the operation mode by minimizing the objective function includes: Set the objective function of the parameter gradient optimization model as where ∈1, ∈2, ∈3, and ∈4 are predefined weight coefficients. When the dynamic association model outputs the control parameter for the k-th time during the adjustment time, E(k) is the energy consumption of the air conditioner when adjusting with the control parameter, is the difference between the indoor relative humidity and the target relative humidity when adjusting with the control parameter, co2(k) is the difference between the indoor carbon dioxide concentration and the target carbon dioxide concentration when adjusting with the control parameter, and T(k) is the difference between the indoor temperature and the target temperature when adjusting with the control parameter; The constraint condition is set as that the control parameters outputted by the dynamic correlation model for the kth time within the adjustment time are all within the numerical range of the operating mode specification; By minimizing the objective function within the adjustment cycle time, when the objective function is minimized, the operation mode switching is completed, and the switched operation mode is used to control the environment in the station.

9. The adaptive energy-saving control method for the internal environment of a subway station according to claim 8, characterized in that The use of the control parameters includes: Step D1: obtaining the control parameters outputted by the dynamic correlation model for the kth time within the adjustment time; Step D2: using PID control to arrange the control parameters on the air conditioner, and using the parameter gradient optimization model to optimize the control parameters; Step D3: repeating steps D1 and D2 until the adjustment time consumption is completed or the objective function is minimized, and the operation mode is switched; Step D4: Use the switched operation mode to control the environment in the station.

10. A method for self-adaptive energy-saving control of the internal environment in a subway station according to claim 9, characterized in that, The visual interface includes a terminal page of a computer or a display interface of a mobile device.

Images