Rail transit station air conditioning system control method based on MPC

Abstract

The invention discloses an MPC-based rail transit station air conditioning system control method, which comprises the following steps: step 1, comparing an outdoor average enthalpy value obtained by prediction and calculation in the past with a set enthalpy value, determining the operation condition of a subway air conditioning system according to a comparison result, and then controlling the on-off states of different fans and air valves; 2, the station hall cold loads are compared to determine a station hall cold load predicted value, and then the valve opening value of a station hall air supply valve is calculated; 3, comparing the cold loads of the subsystems to determine the cold load predicted value of the subsystems, and then calculating the frequency of the draught fan; and step 4, comparing the cold loads of the subsystems to determine the predicted value of the cold loads of the subsystems, and then calculating the opening degree of a group air cold water valve. The problem that an existing subway station air conditioner control system is not associated with factors such as passenger flow, weather, departure logarithm and holidays which affect load changes, and consequently the energy-saving effect of the system is poor is solved.

Description

[Technical field]

[0001] The present invention belongs to the technical field of air-conditioning system control, and in particular relates to a rail transit station air-conditioning system control method based on MPC. [Background technology]

[0002] With the gradual implementation of the dual carbon goals of the rail transit industry and the continuous development of intelligent technology, green and smart have become the new direction of the development of the rail transit industry. The ventilation and air-conditioning system of subway stations is the second largest energy-consuming system in the subway. Due to the serious deviation of the design working conditions from the actual working conditions and the relatively backward existing control mode, the original system has great energy-saving potential.

[0003] The cooling load in the public area of ​​the subway station is affected by outdoor meteorological parameters, piston wind, and changes in passenger flow, and its hourly cooling load varies greatly. In the existing schemes, whether it is traditional single-variable feedback regulation or pure data-driven passive algorithm regulation, there is a lack of mechanism modeling process. The platform and the station hall are not zoning regulated, peak and non-peak passenger flow, working days and non-working days are not time-divided, and the public area A system and B system are not subsystem controlled. Under low-load conditions, the two air-conditioning zones have uneven cooling distribution, excessive cooling, and indoor temperature below the lower limit of the thermal comfort zone, which leads to increased energy consumption of system operation. [Summary of the invention]

[0004] The purpose of the present invention is to provide a rail transit station air-conditioning system control method based on MPC to solve the problem that the existing subway station air-conditioning control system is not associated with factors affecting load changes such as passenger flow, weather, number of departures, holidays, etc., resulting in poor energy-saving effect of the system.

[0005] The present invention adopts the following technical solution: a rail transit station air conditioning system control method based on MPC, comprising the following steps:

[0006] Step 1: Compare the outdoor average enthalpy value obtained by the day-ahead prediction calculation with the set enthalpy value, determine the operating condition of the subway air conditioning system according to the comparison result, and control the switch states of different fans and air valves in the system according to the operating condition;

[0007] Step 2: Compare the station hall cooling load at time T predicted by each node the day before with the station hall cooling load rollingly predicted at time T within the day, determine the station hall cooling load prediction value according to the comparison result, and calculate the station hall air supply valve opening value according to the station hall cooling load prediction value;

[0008] Step 3: Compare the cooling load of the subsystem at time T predicted by the previous day with the cooling load of the subsystem predicted by the intraday rolling forecast at time T, determine the predicted value of the cooling load of the subsystem according to the comparison result, and calculate the fan frequency according to the predicted value of the cooling load of the subsystem;

[0009] Step 4: Compare the cooling load of the subsystem at time T predicted the day before with the cooling load of the subsystem predicted at time T during the day, determine the subsystem cooling load prediction value based on the comparison result, and calculate the opening of the group air cooling water valve based on the subsystem cooling load prediction value.

[0010] Furthermore, the specific method of step 1 is:

[0011] When the outdoor average enthalpy value is ≥ the set enthalpy value, the subway air conditioning system operates according to the small fresh air condition;

[0012] When the outdoor average enthalpy value is less than the set enthalpy value:

[0013] If the outdoor average temperature is ≥ the temperature threshold, the subway air conditioning system will operate according to the fresh air condition;

[0014] If the average outdoor temperature is less than the temperature threshold, the subway air-conditioning system will operate according to the transition season ventilation conditions.

[0015] Furthermore, the specific method of step 2 is:

[0016] When the hall cooling load error is less than the error threshold, and the hall monitoring temperature is less than the lower limit of the hall thermal comfort temperature, the hall air supply valve opening value calculated based on the hall cooling load at time T predicted by each node the day before is directly issued;

[0017] When the station hall cooling load error is less than the error threshold, and the station hall monitoring temperature is within the station hall thermal comfort temperature range, the station hall air supply valve will not operate;

[0018] When the station hall cooling load error is ≥ the error threshold, the station hall cooling load predicted at time T during the day is used to calculate the station hall air supply valve opening value;

[0019] Among them, the station hall cooling load error is the difference between the station hall cooling load at time T predicted node by node the day before and the station hall cooling load rolling forecast at time T within the day; the thermal comfort temperature range of the station hall is 28-30℃.

[0020] Furthermore, the specific method of step 3 is:

[0021] When the subsystem cooling load error is less than the error threshold, and the platform monitoring temperature is less than the lower limit of the platform thermal comfort temperature, the frequencies of the air-conditioning fans and the exhaust fans calculated based on the subsystem cooling load at time T predicted the day before are directly issued;

[0022] When the subsystem cooling load error is ≥ the error threshold, the fan frequency value is calculated using the subsystem cooling load predicted at time T in the intraday rolling forecast;

[0023] Among them, the subsystem cooling load error is the difference between the subsystem cooling load at time T predicted the day before and the subsystem cooling load predicted at time T in the daily rolling forecast; the platform thermal comfort temperature is 27~29℃.

[0024] Furthermore, the specific method of step 4 is:

[0025] When the subsystem cooling load error is less than the error threshold, and the real-time supply air temperature is less than the set supply air temperature lower limit, the group air chilled water valve opening calculated based on the subsystem cooling load predicted at time T will be directly issued;

[0026] When the subsystem cooling load error is ≥ the error threshold, the cooling load of the subsystem predicted at time T during the day is used to calculate the group air-cooled water valve opening value;

[0027] The subsystem cooling load error is the difference between the subsystem cooling load predicted at time T the day before and the subsystem cooling load predicted at time T within the day.

[0028] Furthermore, in step 2, the calculation method of the station hall cooling load is:

[0029] Q i =(Q c，o +Q occ +Q sl +Q lgt +Q eqp ) / 1000,

[0030] In the formula, Q c，o , Q occ , Q sl , Q lgt , Q eqp They are the mechanical fresh air load, personnel load, infiltration load, lighting load and equipment load of the station hall or platform.

[0031] Furthermore, in step 3 and step 4, the calculation method of the cooling load of the subsystem is:

[0032] Q sys =θΣMAX(Q i ,0),

[0033] Where, θ is the cooling load ratio; Q i It is the cooling load of the station hall or platform.

[0034] The beneficial effects of the present invention are:

[0035] 1. The present invention takes into account multivariate influencing factors and combines the passenger flow prediction algorithm, and adopts the model predictive control (MPC) method to achieve optimal control of the rail transit station air-conditioning system based on the original Bas system, thereby improving the energy-saving effect of the system.

[0036] 2. The present invention adopts a system mechanism modeling method of item and area division to predict the cooling load of a large system, which effectively reduces the demand for data volume of the prediction model. It has flexible configuration, can be explained and described, and is convenient for operation and maintenance personnel to systematically grasp the system operation status, and promote intelligent and efficient operation and maintenance.

[0037] 3. The present invention realizes the load prediction of each sub-item and sub-area, and realizes the terminal air volume zoning control of the air conditioning system based on the zoning predicted load, solving the problem of poor cooling capacity distribution between the platform and the station hall. The variable air volume control and group air cooling water valve control of the A-end and B-end air conditioning systems are realized based on the subsystem load, solving the problem that the equipment control is unrelated to the dynamic load.

[0038] 4. The present invention adopts time strategy control, and adopts different optimization control strategies for weekdays, weekends, peak passenger flow periods, and non-peak passenger flow periods, so as to better match the load characteristics of the large system. Through the smart energy management of green stations, the subway air conditioning system can be operated with high efficiency, low carbon, and low cost.

Brief Description of the Drawings

[0039] FIG. 1( a ) and FIG. 1( b ) are diagrams showing the prediction results of inbound and outbound passenger flows, respectively, according to an embodiment of the present invention;

[0040] Figure 2 The predicted load diagram of a subway station hall and platform in an embodiment of the present invention;

[0041] Figure 3 Schematic diagram of the architecture of an air conditioning control system of a subway station in the embodiment. [Specific implementation method]

[0042] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0043] The present invention provides a rail transit station air conditioning system control method based on MPC, MPC stands for model predictive control, that is, based on the item-by-item-by-area system load model, the air conditioning system is controlled by time and area. The rail transit station generally refers to a subway station. Specifically, the following steps are included:

[0044] Step 1: Compare the outdoor average enthalpy value obtained by the day-ahead prediction calculation with the set enthalpy value, determine the operating condition of the subway air conditioning system according to the comparison result, and control the switch states of different fans and air valves in the system according to the operating condition;

[0045] Step 2: Compare the station hall cooling load at time T predicted by each node the day before with the station hall cooling load rollingly predicted at time T within the day, determine the station hall cooling load prediction value according to the comparison result, and calculate the station hall air supply valve opening value according to the station hall cooling load prediction value;

[0046] Step 3: Compare the cooling load of the subsystem at time T predicted by the previous day with the cooling load of the subsystem predicted by the intraday rolling forecast at time T, determine the predicted value of the cooling load of the subsystem according to the comparison result, and calculate the fan frequency according to the predicted value of the cooling load of the subsystem;

[0047] Step 4: Compare the cooling load of the subsystem at time T predicted the day before with the cooling load of the subsystem predicted at time T during the day, determine the subsystem cooling load prediction value based on the comparison result, and calculate the opening of the group air cooling water valve based on the subsystem cooling load prediction value.

[0048] In some embodiments, the specific method of step 1 is:

[0049] When the outdoor average enthalpy value is ≥ the set enthalpy value, the subway air conditioning system operates according to the small fresh air condition. For example, the set enthalpy value can be 67.65kJ / kg, and the temperature threshold can be 19.5℃.

[0050] When the outdoor average enthalpy value is less than the set enthalpy value:

[0051] If the outdoor average temperature is ≥ the temperature threshold, the subway air conditioning system will operate according to the fresh air condition;

[0052] If the average outdoor temperature is less than the temperature threshold, the subway air-conditioning system will operate according to the transition season ventilation conditions.

[0053] In some embodiments, the specific method of step 2 is:

[0054] When the hall cooling load error is less than the error threshold, and the hall monitoring temperature is less than the lower limit of the hall thermal comfort temperature, the hall air supply valve opening value calculated based on the hall cooling load at time T predicted by each node the day before is directly issued;

[0055] When the station hall cooling load error is less than the error threshold, and the station hall monitoring temperature is within the station hall thermal comfort temperature range, the station hall air supply valve will not operate;

[0056] When the station hall cooling load error is ≥ the error threshold, the station hall cooling load predicted at time T during the day is used to calculate the station hall air supply valve opening value;

[0057] The error of the cooling load of the station hall is the difference between the cooling load of the station hall at time T predicted by each node the day before and the cooling load of the station hall predicted by the rolling forecast at time T within the day; the thermal comfort temperature range of the station hall is 28-30°C. The error threshold is set according to the experience value and can be 5-10%.

[0058] In some embodiments, the specific method of step 3 is:

[0059] When the subsystem cooling load error is less than the error threshold, and the platform monitoring temperature is less than the lower limit of the platform thermal comfort temperature, the frequencies of the air-conditioning fans and the exhaust fans calculated based on the subsystem cooling load at time T predicted the day before are directly issued;

[0060] When the subsystem cooling load error is ≥ the error threshold, the fan frequency value is calculated using the subsystem cooling load predicted at time T in the intraday rolling forecast;

[0061] The subsystem cooling load error is the difference between the subsystem cooling load at time T predicted the day before and the subsystem cooling load predicted at time T in the intraday rolling forecast; the platform thermal comfort temperature is 27-29°C. The error threshold is set according to the experience value and can be 5-10%.

[0062] The subway ventilation and air-conditioning system is divided into a water system and an air system. The air system is further divided into a large system and a small system. The large system and the small system are respectively composed of independent subsystems. An independent subsystem is composed of a fresh air system, a supply air system, and a return air system. The main equipment units include: combined air-conditioning processing unit, return and exhaust fan, small fresh air fan, terminal two-way valve and regulating air valve.

[0063] In some embodiments, the specific method of step 4 is:

[0064] When the subsystem cooling load error is less than the error threshold, and the real-time supply air temperature is less than the set supply air temperature lower limit, the group air chilled water valve opening calculated based on the subsystem cooling load predicted at time T will be directly issued;

[0065] When the subsystem cooling load error is ≥ the error threshold, the cooling load of the subsystem predicted at time T during the day is used to calculate the group air-cooled water valve opening value;

[0066] The subsystem cooling load error is the difference between the subsystem cooling load predicted at time T the day before and the subsystem cooling load predicted at time T within the day; the air supply temperature is set according to actual needs. The error threshold is set according to experience, for example, 5-10%.

[0067] In some embodiments, in step 2, the calculation method of the station hall cooling load is:

[0068] Q i =(Q c，o +Q occ +Q sl +Q lgt +Q eqp ) / 1000,

[0069] In the formula, Q c，o , Q occ , Q sl , Q Igt , Qeqp They are the mechanical fresh air load, personnel load, infiltration load, lighting load and equipment load of the station hall or platform.

[0070] Among them, ① The calculation method of mechanical fresh air load is:

[0071] Get the switch status of the fresh air fan, calculate the fresh air load when the fresh air fan is turned on, get the outdoor temperature and relative humidity at time t+1, calculate the outdoor air enthalpy through the enthalpy calculation module, and then calculate the system load according to the fresh air load formula. Then, according to the distribution ratio of the air supply volume in the station hall and the platform, calculate the mechanical fresh air load of the station hall and the platform respectively. The calculation formula is as follows:

[0072] Q c，o =ρ*G o (h w -h n ) / 3.6,

[0073] In the formula, G o is the mechanical fresh air volume, m 3 / h; Volume of air-conditioned area in the station hall, m 3 ; ρ is outdoor air density, kg / m 3 ;h n 、h w are the enthalpy values ​​of indoor and outdoor air respectively, kJ / kg.

[0074] ②The calculation method of personnel load is:

[0075] First, the number of people on the platform and in the station hall is calculated based on the predicted passenger flow data of inbound and outbound passengers. Then, the personnel load of the platform and in the station hall is calculated based on the load calculation formula. The calculation formula is as follows:

[0076]

[0077] Where A1 and A2 are the passenger flow in and out of the station per unit time, person-times; α is the passenger flow peak coefficient; a1 and a2 are the time that incoming passengers stay in the station hall and platform, min; Δt is the time step (data sampling interval), min; b1 and b2 are the time that outgoing passengers stay in the station hall and platform, min;

[0078]

[0079] In the formula, is the clustering coefficient; q s ,q l is the sensible heat and latent heat dissipation of an adult male, W; G i Calculate the number of people in the station hall or platform, people.

[0080] ③The calculation method of penetration load is:

[0081] Obtain the ventilation frequency of the station hall and the volume of the air-conditioning area of ​​the station hall, and calculate the infiltration air volume at the entrance and exit of the station hall; obtain the outdoor temperature and relative humidity at time t+1, calculate the outdoor air enthalpy through the enthalpy calculation module, and then calculate the station hall infiltration load according to the station hall infiltration load formula. The calculation formula is as follows:

[0082] G sl，hall =nV,

[0083] Q slhall =ρ*G sl，hall (h w -h c ) / 3.6,

[0084] In the formula, G slhall is the air volume infiltrating into the station hall from the entrance and exit, m 3 / h; n is the number of ventilation times, times / h; the volume of the air-conditioned area of ​​the station hall, m 3 ; ρ is outdoor air density, kg / m 3 ;h w is the outdoor air enthalpy, kJ / kg; h c is the air enthalpy value at the target temperature and humidity in the station hall, kJ / kg;

[0085] The logarithmic data of train departures during the week and on weekends are obtained from the line network operation management system. The engineer configures the fitting coefficient and gap area, calculates the infiltration air volume from the tunnel to the platform, and further calculates the infiltration load of the platform screen door. The calculation formula is as follows:

[0086] G slpsd =(an 3 +bn 2 -cn+d*f / 1.7,

[0087] Q slpsd =ρ*G al *(h t -h p ) / 3.6,

[0088] In the formula, G slpsd is the air volume that penetrates into the platform through the screen door, m 3 / h; n is the number of train departures, trains / hour; a, b, c, d are polynomial fitting coefficients; f is the penetration gap area of ​​the screen door, m 2 ; ρ is the density of the air leakage from the shield door, kg / m 3 ;h t is the air enthalpy value in the tunnel, kJ / kg; h p is the air enthalpy in the platform area, kJ / kg.

[0089] ④The calculation method of equipment load and lighting load is:

[0090] According to the drawings and the lighting area and the number of heat dissipation equipment obtained on site, the engineer configures the usage coefficient and unit heat dissipation index, and calculates the equipment and lighting load of the station hall and platform. The calculation formula is as follows:

[0091]

[0092] In the formula, are the hourly utilization coefficients of lighting and equipment respectively; e i is the unit heat dissipation index of the equipment in lighting zone i, W / m 2 ; A i is the area of ​​lighting zone i, m 2 ;q i is the heat dissipation index of the device i, W / unit; n i is the number of cooling devices, units.

[0093] In some embodiments, in step 3 and step 4, the calculation method of the cooling load of the subsystem is:

[0094]

[0095] Where, θ is the cooling load ratio; Q i It is the cooling load of the station hall or platform.

[0096] In addition, during the debugging and testing phase of the subway air-conditioning system, engineers continuously calibrate the system load model by item and area based on the indoor temperature and humidity and the actual cooling capacity to ensure that under the same indoor temperature and humidity, the deviation between the actual cooling capacity and the model predicted load is less than 10%.

[0097] Example

[0098] Step 1: Prediction of inbound and outbound passenger flow and outdoor average enthalpy value

[0099] Taking a subway station as an example, its control system architecture is as follows: Figure 3 As shown, the part shown in the dotted box is the original subway control system structure, including a large system control cabinet, a small system control cabinet and a water system group control cabinet. The large system control cabinet and the small system control cabinet are used to connect and control the corresponding fresh air fan, electric air valve, return exhaust fan, air conditioning unit and environmental parameter sensor. The water system group control cabinet is used to connect and control the cooling tower, electric water valve, chilled water pump and chiller.

[0100] Figure 3The part shown in the solid line frame is the structure of the newly added subway control system. The newly added control system includes a frequency conversion control cabinet for the wind system and a frequency conversion control cabinet for the water system. The frequency conversion control cabinet for the wind system connects and controls the electric regulating air valve in the station hall, and also sets exhaust fan frequency converters on all return and exhaust fans, and sets air fan frequency converters on all air-conditioning units. The frequency conversion control cabinet for the water system connects and controls the main pipe cooling meter and temperature sensor, and frequency converters are set on all cooling water pumps and chilled water pumps. The newly added control system is connected to the edge side control cabinet through the intelligent network, and the edge side control cabinet is connected to the meteorological module and the energy-saving system workstation. The edge side control cabinet is also connected to the Bas system in the original system through the intelligent gateway. The Bas system refers to the Building Automation System, that is, the environment and equipment monitoring system. The sub-item and sub-area system load model of the present invention is placed in the edge side controller, which can achieve optimized control of the original system.

[0101] The specific optimization control method is:

[0102] Step 1: The time series prediction model LSTM is used based on 2 months of 30-minute time step data. The first 80% of the data is used for training, and the last 20% of the data set is used for testing. The delay step is set to 96, and the maximum number of training times is 200. The inbound and outbound passenger flows at time t+1 are predicted. The inbound and outbound passenger flow prediction results are shown in Figure 1(a) and Figure 1(b). The error is less than 5%, indicating that the results of the time series prediction model LSTM are accurate.

[0103] Based on the third-party meteorological data, the data of outdoor temperature and humidity at time t+1 are obtained, and the predicted enthalpy value of outdoor air at time t+1 is obtained through the enthalpy calculation module.

[0104] Step 2: Calculate the load by area, item and system, that is, calculate the cooling load at time t+1, specifically:

[0105] 1) Determine the state of the fresh air fan according to the actual operating conditions. In this example, the fresh air fan is shut down and the mechanical fresh air load is 0.

[0106] 2) Calculate the personnel load of the exit hall and the platform using the personnel load calculation formula, and use the in-and-out passenger flow into the following formula to calculate the number of people on the exit hall and platform at time t+1, and further calculate the personnel load of the exit hall and platform using the formula.

[0107] 3) Calculate the infiltration air volume using the station hall and platform infiltration air volume calculation formula, and then get the station hall and platform infiltration load using the infiltration load calculation formula.

[0108] 4) The lighting load of the station hall and platform is obtained according to the lighting calculation formula, and the total equipment heat dissipation load of the public area is obtained according to the equipment heat dissipation load calculation formula. Combined with the proportion of platform and hall equipment heat dissipation load, the equipment load of the station hall and platform is calculated.

[0109] 5) Obtain the cooling load of the station hall and platform based on the partition load calculation formula.

[0110] 6) According to the subsystem load calculation formula, the cooling load of the subsystem is obtained, such as Figure 2 The load shown is bimodal in nature.

[0111] Step 3: Control strategy generation

[0112] 3.1. Calculate the air valve opening according to the station hall load. For example, under rated conditions, the air valve opening and station hall load are ω0 and Q0 respectively, and the lower limit constraint of the valve opening is ω min When the average temperature of the station hall sensor is lower than 28°C, calculate the valve opening at time t+1.

[0113] ω1=ω0*Q0 / Q1,

[0114] ω t+1 =Max(ω1,ω min ),

[0115] Among them, ω1 is the calculated opening of the station hall air valve at time t, ω t+1 Calculate the opening of the station hall air valve at time t+1.

[0116] 3.2. Calculate the water valve opening according to the A / B system load. For example, under rated conditions, the A system load and the blower frequency are Q A.0 、f A.0 , the lower limit constraint of valve opening is ω min When the average temperature of the platform sensor is lower than 27°C, calculate the fan frequency of the air supply fan at time t+1 of this system.

[0117] 3.3. When the group air supply temperature is lower than 21°C during non-peak passenger flow period or lower than 18°C ​​during peak passenger flow period, calculate the group air cooling water valve opening at t+1.

[0118] f A.1 =f A.0 *Q A.0 / Q A.1 ,

[0119] f A.+1 =Max(f A.1 , f A.min ),

[0120]

[0121] in, Calculate the water valve opening of the air-cooled water valve at end A at time t, Calculate the water valve opening for the air-cooled water valve at end A at time t+1. A.0 , is the cooling load and water valve opening of system A under rated conditions, It is the lower limit constraint of the valve opening of the group air cooling water valve.

[0122] 3.4. The frequency of the exhaust fan is adjusted according to the frequency of the supply fan. The frequency of the exhaust fan at time t+1 is calculated by the frequency change rate of the supply fan.

[0123]

[0124] Among them, f Ah.t+1 Calculate the fan frequency for the exhaust fan at end A at time t, f A.1 Calculate the fan frequency for the blower at end A at time t+1.

[0125] In summary, the subway air-conditioning system performs continuous optimization control with step size as frequency according to the above control method.

[0126] The fan frequencies of the A-end blower and the B-end blower of the original system and the present system are shown in Table 1. The air conditioning system of a subway station without an optimization strategy is the original system, and the air conditioning system of a subway station using the control method of the present invention is the present system.

[0127] Table 1 Frequency comparison of the A-end blower and the B-end blower of the original system and this system

[0128]

[0129] As can be seen from Table 1, the original system always maintains a fixed frequency operation. This system can achieve time-sharing and zoning optimization control of the frequency according to multivariate factors such as passenger flow peak hours and weather, saving energy, reducing operating costs, and realizing on-demand energy supply.

[0130] In summary, the present invention considers multivariate influencing factors and combines passenger flow prediction algorithm and expert experience model, adopts model-based predictive control method to replace the original single variable feedback control method, thereby improving the energy-saving effect of the system. The present invention adopts a system mechanism modeling method based on expert experience to predict the cooling load of the large system, which effectively reduces the demand for data volume of the prediction model; it has flexible configuration, explainability and description, which is convenient for operation and maintenance personnel to systematically grasp the operation of the system and help intelligent and efficient operation and maintenance. The present invention realizes the prediction of system load by item and partition, realizes the terminal air volume partition control of the air conditioning system based on the partition prediction load, and solves the problem of poor cold distribution of the platform and the station hall; realizes variable air volume control and group air cooling water valve control of the A-end and B-end air conditioning system based on the subsystem load, and solves the problem that equipment control is unrelated to dynamic load. The present invention adopts time strategy control, and adopts different optimization control strategies for weekdays, weekends, peak passenger flow periods, and non-peak passenger flow periods, so as to better match the load characteristics of the large system; through the intelligent energy management of green stations, the subway air conditioning system is realized to be energy-efficient, low-carbon, and low-cost.

Claims

1. A rail transit station air conditioning system control method based on MPC, characterized in that: The following steps are involved: Step 1: Compare the outdoor average enthalpy value obtained by the day-ahead prediction calculation with the set enthalpy value, determine the operating condition of the subway air conditioning system according to the comparison result, and control the switch states of different fans and air valves in the system according to the operating condition; Step 2: Compare the station hall cooling load at time T predicted by each node the day before with the station hall cooling load rollingly predicted at time T within the day, determine the station hall cooling load prediction value according to the comparison result, and calculate the station hall air supply valve opening value according to the station hall cooling load prediction value; Step 3: Compare the cooling load of the subsystem at time T predicted by the previous day with the cooling load of the subsystem predicted by the intraday rolling forecast at time T, determine the predicted value of the cooling load of the subsystem according to the comparison result, and calculate the fan frequency according to the predicted value of the cooling load of the subsystem; Step 4: Compare the cooling load of the subsystem at time T predicted the day before with the cooling load of the subsystem predicted at time T during the day, determine the subsystem cooling load prediction value based on the comparison result, and calculate the opening of the group air cooling water valve based on the subsystem cooling load prediction value.

2. A rail transit station air conditioning system control method based on MPC as claimed in claim 1, characterized in that: The specific method of step 1 is: When the outdoor average enthalpy value is ≥ the set enthalpy value, the subway air conditioning system operates according to the small fresh air condition; When the outdoor average enthalpy value is less than the set enthalpy value: If the outdoor average temperature is ≥ the temperature threshold, the subway air conditioning system will operate according to the fresh air condition; If the average outdoor temperature is less than the temperature threshold, the subway air-conditioning system will operate according to the transition season ventilation conditions.

3. The MPC-based rail transit station air conditioning system control method according to claim 1, characterized in that: The specific method of step 2 is: When the hall cooling load error is less than the error threshold, and the hall monitoring temperature is less than the lower limit of the hall thermal comfort temperature, the hall air supply valve opening value calculated based on the hall cooling load at time T predicted by each node the day before is directly issued; When the station hall cooling load error is less than the error threshold, and the station hall monitoring temperature is within the station hall thermal comfort temperature range, the station hall air supply valve will not operate; When the station hall cooling load error is ≥ the error threshold, the station hall cooling load predicted at time T during the day is used to calculate the station hall air supply valve opening value; Among them, the station hall cooling load error is the difference between the station hall cooling load at time T predicted node by node the day before and the station hall cooling load rolling forecast at time T within the day; the thermal comfort temperature range of the station hall is 28-30℃.

4. The MPC-based rail transit station air conditioning system control method according to claim 1, characterized in that: The specific method of step 3 is: When the subsystem cooling load error is less than the error threshold, and the platform monitoring temperature is less than the lower limit of the platform thermal comfort temperature, the frequencies of the air-conditioning fans and the exhaust fans calculated based on the subsystem cooling load at time T predicted the day before are directly issued; When the subsystem cooling load error is ≥ the error threshold, the fan frequency value is calculated using the subsystem cooling load predicted at time T in the intraday rolling forecast; Among them, the subsystem cooling load error is the difference between the subsystem cooling load at time T predicted the day before and the subsystem cooling load predicted at time T in the daily rolling forecast; the platform thermal comfort temperature is 27~29℃.

5. The MPC-based rail transit station air conditioning system control method according to claim 1, characterized in that: The specific method of step 4 is: When the subsystem cooling load error is less than the error threshold, and the real-time supply air temperature is less than the set supply air temperature lower limit, the group air chilled water valve opening calculated based on the subsystem cooling load predicted at time T will be directly issued; When the subsystem cooling load error is ≥ the error threshold, the cooling load of the subsystem predicted at time T during the day is used to calculate the group air-cooled water valve opening value; The subsystem cooling load error is the difference between the subsystem cooling load predicted at time T the day before and the subsystem cooling load predicted at time T within the day.

6. The MPC-based rail transit station air conditioning system control method according to claim 1, characterized in that: In step 2, the calculation method of the station hall cooling load is: Q i =(Q c，o +Q oce +Q s1 +Q Igt +Q eqp ) / 1000, In the formula, Q c，o , Q occ , Q s1 , Q Igt , Q eqp They are the mechanical fresh air load, personnel load, infiltration load, lighting load and equipment load of the station hall or platform.

7. The MPC-based rail transit station air conditioning system control method according to claim 1, characterized in that: In step 3 and step 4, the calculation method of the cooling load of the subsystem is: Q sys =θΣMAX(Q i ,0), Where, θ is the cooling load ratio; Q i It is the cooling load of the station hall or platform.

Images