Energy-saving and carbon-reducing multi-objective optimization method and device for cold source system of high-speed rail station

Abstract

The invention provides an energy-saving and carbon-reducing multi-objective optimization method and device for a cold source system of a high-speed rail station, and the method comprises the steps: building an air-conditioning cooler system load prediction model and a human body comfort model based on the historical data of an air-conditioning cooler system, the historical data of the internal and external environments of the high-speed rail station, and the thermal comfort evaluation historical data of the internal environment of the high-speed rail station; a multi-objective optimization algorithm is established with minimization of the sum of the air conditioner refrigerator system load and the human body comfort as an optimization objective, and the weight of the air conditioner refrigerator system load and the human body comfort can be adjusted according to real-time data of the internal environment and the external environment of the high-speed rail station; and a multi-objective optimization algorithm is solved, and cold machine optimization control is carried out according to the air conditioner cold machine system load solution value and the air conditioner cold machine system load current value, so that the reliability of energy-saving and carbon-reducing multi-objective optimization of the high-speed rail station cold source system is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of air-conditioning system optimization, and particularly to an energy-saving and carbon-reducing multi-objective optimization method and device for a cold source system in a high-speed railway station. Background Art

[0002] With the acceleration of the urbanization process and the rapid development of the high-speed railway network, as a transportation hub, the high-speed railway station faces the need to receive a large number of passengers. In such a high-traffic environment, maintaining a comfortable indoor temperature and humidity is crucial. However, the operating energy consumption of the cold source system in the high-speed railway station is relatively high, and the operating state of the cold source system has a great impact on energy consumption and carbon emissions. Therefore, how to optimize the cold source system to reduce energy consumption and carbon emissions while ensuring a comfortable indoor environment has become an urgent problem to be solved.

[0003] Currently, although some cold source systems can be adjusted by artificial intelligence methods, most traditional systems still operate based on a certain set of fixed parameters, without fully considering the environmental changes, load demands, and comfort requirements in the high-speed railway station. Moreover, the weights of different optimization objectives are fixed and cannot be adjusted in a timely manner according to the changes in the internal and external environments of the high-speed railway station and the changes in the passenger flow, resulting in low reliability of the energy-saving and carbon-reducing multi-objective optimization of the cold source system in the high-speed railway station.

[0004] In view of this problem, the present invention provides an energy-saving and carbon-reducing multi-objective optimization method and device for a cold source system in a high-speed railway station to solve the above problems. Summary of the Invention

[0005] In order to solve the problems existing in the prior art, the present invention innovatively proposes an energy-saving and carbon-reducing multi-objective optimization method and device for a cold source system in a high-speed railway station, effectively solving the problem of low reliability of the energy-saving and carbon-reducing multi-objective optimization of the cold source system in the high-speed railway station caused by the prior art, and effectively improving the reliability of the energy-saving and carbon-reducing multi-objective optimization of the cold source system in the high-speed railway station.

[0006] The first aspect of the present invention provides an energy-saving and carbon-reducing multi-objective optimization method for a cold source system in a high-speed railway station, including:

[0007] Obtaining historical data of the air-conditioning chiller system, real-time data of the air-conditioning chiller system, historical data of the internal and external environments of the high-speed railway station, real-time data of the internal and external environments of the high-speed railway station, historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, and real-time data of the thermal comfort evaluation of the internal environment of the high-speed railway station, including timestamp information;

[0008] Based on the historical data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, and the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, establishing a load prediction model and a human comfort model for the air-conditioning chiller system;

[0009] Taking the minimization of the sum of the air-conditioning chiller system load and human comfort as the optimization objective, a multi-objective optimization algorithm is established. Among them, the weights of the air-conditioning chiller system load and human comfort can be adjusted according to the real-time data of the internal and external environments of the high-speed railway station;

[0010] Solve the multi-objective optimization algorithm, and perform chiller optimization control according to the solved value of the air-conditioning chiller system load and the current value of the air-conditioning chiller system load.

[0011] Optionally, based on the historical data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, and the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, the establishment of the air-conditioning chiller system load prediction model and the human comfort model specifically includes:

[0012] Taking the air-conditioning chiller system load as the output and the historical data of the internal and external environments of the high-speed railway station as the input, based on the historical data of the air-conditioning chiller system and the historical data of the internal and external environments of the high-speed railway station, establish and train an LSTM time series model to predict the future load of the air-conditioning chiller system;

[0013] Taking the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station as the output and the historical data of the internal and external environments of the high-speed railway station as the input, based on the historical data of the air-conditioning chiller system and the historical data of the internal and external environments of the high-speed railway station, establish and train a PMV model based on different time periods to predict the thermal comfort under a certain set of internal and external environment data of the high-speed railway station at different time periods.

[0014] Optionally, the objective function of the multi-objective optimization algorithm is specifically: [[ID=q17]]

[0015] min(w1(t)·E ac (t)+w2(t)·Deviations from Comfort(t))

[0016] Wherein, w1(t) is the weight of the energy-saving target at time t, E ac (t) is the energy consumption of the air-conditioning chiller system at time t, w2(t) is the weight of the thermal comfort target at time t, and Deviations from Comfort(t) is the thermal comfort at time t.

[0017] Furthermore, the adjustment of the weights of the air-conditioning chiller system load and human comfort according to the real-time data of the internal and external environments of the high-speed railway station is specifically:

[0018] w2(t)=α0·e PMV(t)·N(t)

[0019] Wherein, α0 is the initial weight of thermal comfort, PMV(t) is the PMV value under the internal and external environment data of the high-speed railway station at the current time t, and N(t) is the current passenger flow in the high-speed railway station;

[0020] w1(t)=1-w2(t)

[0021] Among them, w1(t) is the weight of the air-conditioning chiller system load.

[0022] Optionally, solving the multi-objective optimization algorithm and performing chiller optimization control according to the solved value of the air-conditioning chiller system load and the current value of the air-conditioning chiller system load specifically includes:

[0023] Solving for the air-conditioning chiller system load corresponding to the minimum of the objective function. When the solved value of the air-conditioning chiller system load is greater than the current value of the air-conditioning system chiller load, and the difference between the solved value of the air-conditioning chiller system load and the current value of the air-conditioning system chiller load is greater than the first preset threshold, select some chillers to start; when the solved value of the air-conditioning chiller system load is less than the current value of the air-conditioning system chiller load, and the difference between the current value of the chiller load and the solved value of the chiller load is greater than the first preset threshold, select some chillers to shut down.

[0024] Furthermore, the selection of starting or shutting down some chillers specifically is:

[0025] Obtaining the corresponding relationship between the solved values of the air-conditioning chiller system load at different levels and the operating efficiency of the chiller system under any combination of all chillers in the current air-conditioning chiller system; [[ID=??]] [[ID=??]]

[0026] Select the chiller combination with the highest operating efficiency of the chiller system in the current air-conditioning chiller system at a certain solved value of the air-conditioning chiller system load for operation. If a certain chiller is in this chiller combination and its current operating state is off, then select this chiller to start; if a certain chiller is not in this chiller combination and its current operating state is on, then select this chiller to shut down.

[0027] Optionally, before establishing the multi-objective optimization algorithm with the minimization of the sum of the air-conditioning chiller system load and human comfort as the optimization goal, it further includes:

[0028] Obtaining the historical data of the water pump in the air-conditioning chiller system including timestamp information and the real-time data of the water pump in the air-conditioning chiller system;

[0029] Based on the historical data of the water pump in the air-conditioning chiller system and the real-time data of the water pump in the air-conditioning chiller system, with the power of the water pump in the air-conditioning chiller system as the output and the historical data of the operating frequency of the water pump, the historical data of the water pump outlet pressure, and the historical data of the water pump outlet flow rate as the input, establish and train a water pump power consumption prediction model to predict the water pump power under a certain air-conditioning chiller system load.

[0030] Optionally, solving the multi-objective optimization algorithm and performing chiller optimization control according to the solved value of the air-conditioning chiller system load and the current value of the air-conditioning chiller system load specifically includes:

[0031] Note: There seems to be an error in the original text where the line numbers for "Obtaining the corresponding relationship between the solved values of the air-conditioning chiller system load at different levels and the operating efficiency of the chiller system under any combination of all chillers in the current air-conditioning chiller system;" are incorrect in the provided text. It should be instead of [[ID=??]] in the English translation for proper alignment. Also, the text might need further review for overall clarity and accuracy in the patent context.Solve for the load of the air-conditioning chiller system when the objective function is minimized. When the solved value of the air-conditioning chiller system load is greater than the current value of the air-conditioning system chiller load, and the difference between the solved value of the air-conditioning chiller system load and the current value of the air-conditioning system chiller load is not greater than the first preset threshold, increase the operating frequency of the water pump, or decrease the chiller outlet water temperature; when the solved value of the air-conditioning chiller system load is less than the current value of the air-conditioning system chiller load, and the difference between the current value of the chiller load and the solved value of the chiller load is not greater than the first preset threshold, decrease the operating frequency of the water pump, or increase the chiller outlet water temperature.

[0032] Further, until the difference between the solved value of the air-conditioning chiller system load and the current value of the air-conditioning system chiller load, or the difference between the current value of the air-conditioning chiller system load and the solved value of the air-conditioning system chiller load is not greater than the second preset threshold, where the second preset threshold is less than the first preset threshold.

[0033] The second aspect of the present invention provides an energy-saving and carbon-reducing multi-objective optimization device for a cold source system in a high-speed railway station, including:

[0034] An acquisition module that acquires historical data of the air-conditioning chiller system including timestamp information, real-time data of the air-conditioning chiller system, historical data of the internal and external environments of the high-speed railway station, real-time data of the internal and external environments of the high-speed railway station, historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, and real-time data of the thermal comfort evaluation of the internal environment of the high-speed railway station;

[0035] A first establishment module that establishes an air-conditioning chiller system load prediction model and a human comfort model based on the historical data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, and the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station;

[0036] A second establishment module that establishes a multi-objective optimization algorithm with the minimization of the sum of the air-conditioning chiller system load and human comfort as the optimization objective, where the weights of the air-conditioning chiller system load and human comfort can be adjusted according to the real-time data of the internal and external environments of the high-speed railway station;

[0037] An optimization control module that solves the multi-objective optimization algorithm and performs chiller optimization control according to the solved value of the air-conditioning chiller system load and the current value of the air-conditioning chiller system load.

[0038] The technical solutions adopted by the present invention include the following technical effects:

[0039] 1. Based on the historical data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, and the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, the present invention establishes a load prediction model for the air-conditioning chiller system and a human comfort model; taking the minimization of the sum of the load of the air-conditioning chiller system and human comfort as the optimization goal, a multi-objective optimization algorithm is established, wherein the weights of the load of the air-conditioning chiller system and human comfort can be adjusted according to the real-time data of the internal and external environments of the high-speed railway station; solving the multi-objective optimization algorithm, and performing chiller optimization control according to the solved value of the load of the air-conditioning chiller system and the current value of the load of the air-conditioning chiller system, effectively solving the problem of low reliability of the multi-objective optimization of energy conservation and carbon reduction of the cold source system in the high-speed railway station caused by the existing technology, and effectively improving the reliability of the multi-objective optimization of energy conservation and carbon reduction of the cold source system in the high-speed railway station.

[0040] 2. In the technical solution of the present invention, the weights of the load of the air-conditioning chiller system and human comfort can be adjusted according to the real-time data of the internal and external environments of the high-speed railway station, which not only considers the internal and external environmental factors of the high-speed railway station, but also considers the current passenger flow inside the high-speed railway station, further improving the reliability of the multi-objective optimization of energy conservation and carbon reduction of the cold source system in the high-speed railway station.

[0041] 3. In the technical solution of the present invention, when selecting a certain solved value of the load of the air-conditioning chiller system, the chiller combination with the highest operating efficiency in the current chiller system of the air-conditioning chiller system is selected for operation. If a certain chiller is in the chiller combination and the current opening state of the chiller is closed, then the chiller is selected to be turned on; if a certain chiller is not in the chiller combination and the current opening state of the chiller is on, then the chiller is selected to be turned off, ensuring the operating efficiency of the chiller in the air-conditioning system.

[0042] 4. In the technical solution of the present invention, when the solved value of the load of the air-conditioning chiller system is greater than the current value of the load of the chiller in the air-conditioning system, and the difference between the solved value of the load of the air-conditioning chiller system and the current value of the load of the chiller in the air-conditioning system is not greater than the first preset threshold, the operating frequency of the water pump is increased, or the outlet water temperature of the chiller is decreased; when the solved value of the load of the air-conditioning chiller system is less than the current value of the load of the chiller in the air-conditioning system, and the difference between the current value of the load of the chiller and the solved value of the load of the chiller is not greater than the first preset threshold, the operating frequency of the water pump is decreased, or the outlet water temperature of the chiller is increased, ensuring the applicability of the chiller optimization control in the cold source system of the high-speed railway station.

[0043] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0045] Figure 1 It is a schematic flowchart of the method of Embodiment 1 in the solution of the present invention;

[0046] Figure 2 It is a schematic diagram (1) of the corresponding relationship between the solution values of the load of different air-conditioning chiller systems in the method of Embodiment 1 in the present invention and the operating efficiency of the chiller system under any combination of all chillers in the current air-conditioning chiller system;

[0047] Figure 3 It is a schematic diagram (2) of the corresponding relationship between the solution values of the load of different air-conditioning chiller systems in the method of Embodiment 1 in the present invention and the operating efficiency of the chiller system under any combination of all chillers in the current air-conditioning chiller system;

[0048] Figure 4 It is a schematic diagram (3) of the corresponding relationship between the solution values of the load of different air-conditioning chiller systems in the method of Embodiment 1 in the present invention and the operating efficiency of the chiller system under any combination of all chillers in the current air-conditioning chiller system;

[0049] Figure 5 It is a schematic diagram (4) of the corresponding relationship between the solution values of the load of different air-conditioning chiller systems in the method of Embodiment 1 in the present invention and the operating efficiency of the chiller system under any combination of all chillers in the current air-conditioning chiller system;

[0050] Figure 6 It is another schematic flowchart of the method of Embodiment 1 in the solution of the present invention;

[0051] Figure 7 It is a schematic structural diagram of the device of Embodiment 2 in the present invention. Detailed implementation manners

[0052] To clearly illustrate the technical features of this solution, the present invention will be elaborated in detail below through specific implementation manners and in conjunction with its accompanying drawings. The following disclosure provides many different embodiments or examples for implementing different structures of the present invention. To simplify the disclosure of the present invention, the components and settings of specific examples are described below. In addition, the present invention may repeat reference numerals and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not in itself indicate the relationship between the various embodiments and / or settings discussed. It should be noted that the components illustrated in the drawings are not necessarily drawn to scale. The present invention omits the description of well-known components and processing techniques and processes to avoid unnecessarily limiting the present invention.

[0053] Embodiment 1

[0054] As Figure 1 shown, the present invention provides an energy-saving, carbon-reducing and multi-objective optimization method for the cold source system of high-speed railway stations, including:

[0055] S1, Obtain the historical data of the air-conditioning chiller system including timestamp information, the real-time data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, the real-time data of the internal and external environments of the high-speed railway station, the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, and the real-time data of the thermal comfort evaluation of the internal environment of the high-speed railway station;

[0056] S3, Based on the historical data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, and the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, establish a load prediction model and a human comfort model for the air-conditioning chiller system;

[0057] S5, Taking the minimization of the sum of the load of the air-conditioning chiller system and human comfort as the optimization goal, establish a multi-objective optimization algorithm, where the weights of the load of the air-conditioning chiller system and human comfort can be adjusted according to the real-time data of the internal and external environments of the high-speed railway station;

[0058] S7, Solve the multi-objective optimization algorithm, and perform chiller optimization control according to the solved value of the load of the air-conditioning chiller system and the current value of the load of the air-conditioning chiller system.

[0059] Among them, in step S1, through sensors and Internet of Things technology, relevant data of the air-conditioning chiller system are collected in real time, including load demand (load of the air-conditioning chiller system), chiller outlet water temperature, refrigeration power, current, voltage, flow rate (collect data through sensors and Internet of Things technology, collect the original data of all chillers, and the data is collected with a timestamp, and the time granularity is minute-level), etc.

[0060] At the same time, collect external environment data (such as outdoor temperature, humidity, air velocity, etc. (distance is not considered, the data is collected with a timestamp, and the granularity is minute-level)) and the status data of chiller equipment (such as chiller speed, compressor operating status, pump power, pump operating frequency, pump outlet water temperature, pump outlet pressure, etc., the data is collected with a timestamp, and the granularity is minute-level).

[0061] Perform preprocessing operations such as cleaning and normalization on the collected original data to eliminate noise data.

[0062] Normalization:

[0063] Among them, x is the original data, min(x) and max(x) are the minimum and maximum values of the data respectively, and x′ is the normalized data

[0064] In step S3, based on the historical data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, and the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, establishing a load prediction model and a human comfort model for the air-conditioning chiller system specifically includes:

[0065] S31. With the load of the air-conditioning chiller system as the output and the historical data of the internal and external environments of the high-speed railway station as the input, based on the historical data of the air-conditioning chiller system and the historical data of the internal and external environments of the high-speed railway station, establish and train an LSTM time series model to predict the future load of the air-conditioning chiller system;

[0066] S32. With the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station as the output and the historical data of the internal and external environments of the high-speed railway station as the input, based on the historical data of the air-conditioning chiller system and the historical data of the internal and external environments of the high-speed railway station, establish and train a PMV model based on different time periods to predict the thermal comfort under a certain set of internal and external environment data of the high-speed railway station at different time periods.

[0067] Among them, in step S31, based on the historical load data and environmental parameters, train the LSTM time series model to predict the future load demand of the air-conditioning chiller system, ensuring that the system can respond in advance.

[0068] LSTM (Long Short-Term Memory) is a special type of Recurrent Neural Network (RNN) that solves the problems of vanishing gradients and exploding gradients that occur in traditional RNNs during long sequence training. LSTM controls the flow of information by introducing three gating mechanisms: the input gate, the forget gate, and the output gate.

[0069] The following are the core mathematical formulas of LSTM:

[0070] 1. Forget gate

[0071] The forget gate determines how much information from the previous cell state will be discarded. The output of the forget gate is a value between 0 and 1, indicating how much of the previous information should be retained.

[0072] f t = σ(W f · [h t-1 , x t + b f )

[0073] Where:

[0074] f t is the output of the forget gate (a value between 0 and 1),

[0075] W f is the weight matrix of the forget gate,

[0076] h t-1 is the hidden state at the previous time step,

[0077] xt is the input at the current time t,

[0078] b f is the bias.

[0079] 2. Input Gate

[0080] The input gate controls how much of the input information at the current time is added to the cell state. It has two parts: one is the "input gate" i that determines which values will be updated t , and the other is the one that generates the candidate values

[0081] i t = σ(W i · [h t-1 , x t + b i )

[0082]

[0083] Where:

[0084] i t is the output of the input gate,

[0085] is the candidate cell state (also known as candidate memory),

[0086] W i , W C are the weight matrices of the input gate and the candidate state,

[0087] b i , b C are the biases of the input gate and the candidate state.

[0088] 3. Update Cell State

[0089] The cell state C at the current time t is updated through the combination of the forget gate and the input gate.

[0090] The cell state is the core of the LSTM and records the long-term memory of the time step.

[0091]

[0092] Where:

[0093] C t is the cell state at the current time t,

[0094] C t-1 is the cell state at the previous time,

[0095] * denotes element-wise multiplication.

[0096] 4. Output Gate

[0097] The output gate determines which parts of the current cell state will be output as the hidden state ht. The hidden state will serve as the output of the network and will also be passed to the next time step.

[0098] o t = σ(W o · [h t-1 , x t + b o )

[0099] h t = o t * tanh(C t )

[0100] Where:

[0101] o t is the output of the output gate,

[0102] b o is the bias of the output gate,

[0103] h t is the hidden state at the current time step (the output of the network).

[0104] In step S32, considering the human comfort temperature and humidity range, combined with different time periods and environmental parameters, the system settings are dynamically adjusted to ensure comfort.

[0105] The human comfort model is usually used to quantify the human comfort feeling towards the environment, especially the comfort in a thermal environment. The comfort models used here are the PMV (Predicted Mean Vote) model and the PPD (Predicted Percentage of Dissatisfied) model, both of which are proposed based on the thermal comfort theory and are used to evaluate the comfort of the human body under certain environmental conditions.

[0106] 1. PMV Model (Predicted Mean Vote)

[0107] The PMV model is a widely adopted comfort evaluation standard internationally. It predicts the human comfort level based on the human thermal sensation towards the environment (temperature, humidity, wind speed, etc.), and finally gives a score ranging from -3 (very cold) to +3 (very hot). The PMV model is based on the heat transfer principle and considers the heat balance of the human body, that is, the heat exchange between the human body and the environment. The PMV value reflects the overall thermal comfort of the human body:

[0108] PMV > 0: The environmental temperature is relatively high, and the human body feels hot.

[0109] PMV = 0: The human body feels comfortable.

[0110] PMV < 0: The environmental temperature is relatively low, and the human body feels cold.

[0111]

[0112] Where:

[0113] M: The metabolic rate of the human body (unit: W / m 2 ), representing the activity intensity, usually using the standard value of human resting metabolism.

[0114] W: The external work of the human body (unit: W / m 2 ), usually defaulted to 0, indicating that the human body does not perform external work.

[0115] Pa: Vapor pressure (unit: Pa), calculated from humidity.

[0116] Ta: The air temperature outside the high-speed railway station (unit: °C).

[0117] Tr: Radiation temperature (unit: °C), the temperature of the inner surface of the station (walls, windows, floors, etc.).

[0118] f cl : Clothing surface area coefficient, indicating the heat insulation effect of clothing.

[0119] T c l: Clothing surface temperature (unit: °C), generally the human skin temperature.

[0120] h c : Air convection heat transfer coefficient, depending on the wind speed.

[0121] The PPD value represents the percentage of people who feel uncomfortable under given environmental conditions. It is calculated from the PMV value and is used to quantify the proportion of dissatisfaction. The calculation formula of PPD is as follows:

[0122]

[0123] Interpretation of the PPD value

[0124] PPD < 10%: The vast majority (more than 90%) of people feel comfortable.

[0125] PPD = 50%: Half of the people feel comfortable and half feel uncomfortable.

[0126] PPD > 10%: More people feel uncomfortable.

[0127] Among them, in step S5, the objective function of the multi-objective optimization algorithm is specifically:

[0128] min(w1(t)·E ac (t)+w2(t)·Deviations from Comfort(t))

[0129] Among them, w1(t) is the weight of the energy-saving objective at time t, and E ac (t) is the energy consumption of the air-conditioning chiller system at time t. w2(t) is the weight of the thermal comfort objective at time t, and Deviations from Comfort(t) is the thermal comfort; or the deviation of human comfort, measured by PMV, that is, the PMV value.

[0130] The energy consumption E ac (t) of the air-conditioning chiller system is a variable. Determine the energy consumption E ac (t) of the air-conditioning chiller system corresponding to the minimum of the objective function, that is, the solution value of the air-conditioning chiller system load (the solution value of the chiller load).

[0131] Specifically, by adjusting the weight between comfort and energy saving according to the changes in the current environment (such as the number of people and external temperature and humidity), the operation of the air conditioner is optimized. Assuming that under different environmental conditions, the priorities of energy saving and comfort are different, the adaptive weights w1(t) and w2(t) are set. Specifically, the weights of the air-conditioning chiller system load and human comfort can be adjusted according to the real-time data of the internal and external environments of the high-speed railway station, specifically:

[0132] w2(t)=α0·e PMV(t)·N(t)

[0133] Among them, α0 is the initial weight of thermal comfort, PMV(t) is the PMV value under the internal and external environment data of the high-speed railway station at the current time t, and N(t) is the current number of people in the high-speed railway station;

[0134] w1(t)=1 - w2(t)

[0135] Among them, w1(t) is the weight of the air-conditioning chiller system load.

[0136] For example, when the number of people N(t) is high or PMV(t) is high, the weight w2(t) of comfort can be increased to ensure people's comfort; when the number of people N(t) is low or PMV(t) is appropriate, the weight w1(t) of energy saving can be increased to reduce the energy consumption of the air conditioner.

[0137] The cold machine energy consumption is a variable. Determine the cold machine energy consumption corresponding to the minimum of the objective function, that is, the solution value of the cold machine load. According to the solution value of the cold machine load and the current value of the cold machine load, perform cold machine start / stop control. If the requirements are not met, use the refrigeration capacity formula to adjust the operating parameters allocated to each cold machine, and use the predicted model of the water pump power consumption to adjust the cold machine outlet water temperature, water pump operating frequency, etc.

[0138] Among them, in step S7, solve the multi-objective optimization algorithm. According to the solution value of the air-conditioning cold machine system load and the current value of the air-conditioning cold machine system load, the specific cold machine optimization control includes:

[0139] Solve the air-conditioning cold machine system load corresponding to the minimum of the objective function. When the solution value of the air-conditioning cold machine system load is greater than the current value of the air-conditioning system cold machine load, and the difference between the solution value of the air-conditioning cold machine system load and the current value of the air-conditioning system cold machine load is greater than the first preset threshold, select some cold machines to start; when the solution value of the air-conditioning cold machine system load is less than the current value of the air-conditioning system cold machine load, and the difference between the current value of the cold machine load and the solution value of the cold machine load is greater than the first preset threshold, select some cold machines to shut down.

[0140] Specifically, the selection of some cold machines to start or shut down is specifically as follows:

[0141] Obtain the corresponding relationship between the solution values of different air-conditioning cold machine system loads and the operating efficiency of the cold machine system under any combination of all cold machines in the current air-conditioning cold machine system (it can be a database or in the form of an attached drawing);

[0142] Select the cold machine combination with the highest operating efficiency of the cold machine system in the current air-conditioning cold machine system when a certain air-conditioning cold machine system load solution value is reached. If a certain cold machine is in this cold machine combination and the current on / off state of this cold machine is off, then select this cold machine to start; if a certain cold machine is not in this cold machine combination and the current on / off state of this cold machine is on, then select this cold machine to shut down.

[0143] Taking the corresponding relationship in the form of an attached drawing as an example, the horizontal axis is the cold load demand of the air-conditioning cold machine system (solution value of the air-conditioning cold machine system load), with the unit of kw, and the vertical axis is the refrigeration efficiency COP of the cold machine The air-conditioning cold machine system includes the 2# main machine, 3# main machine, and 4# main machine.

[0144] As Figure 2 shown, in the working condition where the cold load demand of the air-conditioning cold machine system is 1700 to 2400 KW, the efficiency of only starting the 3# main machine (No. 3 cold machine) is higher than the efficiency of starting both the 2# (No. 2 cold machine) and 3# at the same time. Therefore, the cold machine combination with the highest operating efficiency of the cold machine system in the current air-conditioning cold machine system is the 3# main machine. Since the No. 2 cold machine is not in this cold machine combination and the current on / off state of the No. 2 cold machine is on, then select the No. 2 cold machine to shut down.

[0145] As Figure 3 shown, in the working condition where the cooling load demand of the air-conditioning chiller system is 1700 to 2700 KW, the efficiency of only turning on the 4# main unit (No. 4 chiller) is higher than that of turning on both the 2# (No. 2 chiller) and 4# at the same time. Therefore, the chiller combination with the highest operating efficiency in the current air-conditioning chiller system is the 4# main unit. Because the 2# chiller is not in this chiller combination and the current operating state of the 2# chiller is on, then the 2# chiller is selected to be turned off.

[0146] As Figure 4 shown, in the working condition where the cooling load demand of the air-conditioning chiller system is 3100 to 5300 KW, the efficiency of only turning on the 3# main unit (No. 3 chiller) and the 2# main unit (No. 2 chiller) is higher than that of turning on the 2# main unit (No. 2 chiller), the 3# main unit (No. 3 chiller) and the 4# main unit at the same time. Therefore, the chiller combination with the highest operating efficiency in the current air-conditioning chiller system is the 3# main unit and the 2# main unit. Because the 4# chiller is not in this chiller combination and the current operating state of the 4# chiller is on, then the 4# chiller is selected to be turned off.

[0147] As Figure 5 shown, in the working condition where the cooling load demand of the air-conditioning chiller system is 3100 to 5300 KW, the efficiency of only turning on the 4# main unit (No. 4 chiller) and the 4# main unit (No. 2 chiller) is higher than that of turning on the 2# main unit (No. 2 chiller), the 3# main unit (No. 3 chiller) and the 4# main unit at the same time. Therefore, the chiller combination with the highest operating efficiency in the current air-conditioning chiller system is the 4# main unit and the No. 2 main unit. Because the 3# chiller is not in this chiller combination and the current operating state of the 3# chiller is on, then the 3# chiller is selected to be turned off.

[0148] It should be noted that Figures 2 - 5 only examples of selecting some chillers to be turned off are given, which are only for explanatory purposes. The idea of selecting some chillers to be turned on is similar to that of selecting some chillers to be turned off, and this embodiment will not be elaborated here.

[0149] As Figure 6 shown, the technical solution of the present invention also provides an energy-saving and carbon-reducing multi-objective optimization method for the cold source system of high-speed railway stations. Before step S5, it further includes:

[0150] S4, obtaining the historical data of the water pumps in the air-conditioning chiller system including timestamp information and the real-time data of the water pumps in the air-conditioning chiller system; based on the historical data of the water pumps in the air-conditioning chiller system and the real-time data of the water pumps in the air-conditioning chiller system, taking the water pump power in the air-conditioning chiller system as the output, and taking the historical data of the operating frequency of the water pumps, the historical data of the water outlet pressure of the water pumps and the historical data of the water outlet flow of the water pumps as the input, establishing and training a water pump power consumption prediction model to predict the water pump power under a certain load of the air-conditioning chiller system.

[0151] Specifically, a linear regression method is adopted: based on the known data set (the historical data of the water pump in the air-conditioning chiller system including timestamp information), the parameters w of the linear regression model are trained by the method of gradient descent, so as to judge the trend of the curve according to the positive or negative of the parameter w.

[0152] The model is defined as: f(x) = w0 + w1x1 + w2x2 +... + w n x n .

[0153] Represented by a matrix, it is f(x) = XW, where: is a series of required parameters, is the input data matrix, including the pump operating frequency, the pump outlet pressure, the pump outlet flow rate, etc. Because the constant term w0 is considered, a column of 1s is added to the first column of X. One row of X can be regarded as a complete input data, n represents that a data has n attributes (features), and m rows represent a total of m data. The data set label is The goal of the linear regression model is to find a series of parameters w to make f(x) = XW as close to y as possible.

[0154] Here, the Huber loss function is used. The Huber loss function is a loss function that combines the advantages of the L1 loss and the L2 loss, and has stronger robustness to outliers during model fitting.

[0155]

[0156] Among them: δ is a hyperparameter that determines the threshold for switching between the L1 and L2 losses.

[0157] When the residual is less than δ, the Huber loss is the same as the L2 loss, and it has smoothness and differentiability;

[0158] When the residual is greater than δ, the Huber loss switches to the L1 loss, which has less impact on outliers.

[0159] Furthermore, corresponding to the solution of the multi-objective optimization algorithm in step S7, according to the solved value of the air-conditioning chiller system load and the current value of the air-conditioning chiller system load, the specific cold chiller optimization control includes:

[0160] Solve for the load of the air-conditioning chiller system when the objective function is minimized. When the solved value of the air-conditioning chiller system load is greater than the current value of the air-conditioning system chiller load, and the difference between the solved value of the air-conditioning chiller system load and the current value of the air-conditioning system chiller load is not greater than the first preset threshold, increase the operating frequency of the water pump, or decrease the chilled water outlet temperature; when the solved value of the air-conditioning chiller system load is less than the current value of the air-conditioning system chiller load, and the difference between the current value of the chiller load and the solved value of the chiller load is not greater than the first preset threshold, decrease the operating frequency of the water pump, or increase the chilled water outlet temperature.

[0161] Chiller optimization control algorithm: Based on the prediction results output by the model, dynamically adjust the operating parameters of the chiller (such as chiller switch, operating frequency of the water pump, chilled water outlet temperature, etc.) to ensure that the system energy consumption is minimized while meeting the load requirements. Among them, the chilled water outlet temperature (chilled water outlet temperature) can be inversely deduced from the solved value of the air-conditioning chiller system load and the industrial refrigeration capacity formula. The industrial refrigeration capacity formula is as follows:

[0162] Refrigeration capacity (predicted load of the air-conditioning chiller system load prediction model, that is, the solved value of the air-conditioning chiller system load) = chilled water flow * 4.187 * temperature difference * coefficient; where, the chilled water flow refers to the required cold water flow when the chiller is working, and the unit needs to be converted to liters / second; the temperature difference refers to the temperature difference between the inlet and outlet water of the chiller; 4.187 is a fixed value (specific heat capacity of water); the coefficient is 1.3 when selecting an air-cooled chiller and 1. if selecting a water-cooled chiller. That is, the corresponding chilled water outlet temperature can be deduced based on the solved value of the air-conditioning chiller system load.

[0163] Adjust the chilled water outlet temperature according to the temperature requirements in the cold station. This requires considering factors such as the population density and external environmental temperature for dynamic adjustment.

[0164] Temperature adjustment: Balance energy conservation and comfort by precisely adjusting the chilled water outlet temperature to avoid unnecessary overcooling. For example, during off-peak hours, when the number of people is small and the external temperature is low, the outlet temperature can be moderately increased to reduce the refrigeration load.

[0165] Outlet temperature optimization: Adopt an adaptive control algorithm to dynamically adjust the outlet temperature by real-time monitoring of factors such as indoor temperature and humidity, external environmental temperature, and chiller load to ensure that the system operates in the optimal energy efficiency state.

[0166] The operating frequency of the water pump directly affects the energy consumption of the water pump (independent of the chiller energy consumption), and the operating frequency of the water pump can be dynamically adjusted according to actual needs to avoid waste of electric energy due to overoperation.

[0167] Water pump adjustment control strategy:

[0168] Water pump frequency adjustment: Through variable frequency control technology, the frequency of the water pump is adjusted according to the changes in the load of the chiller and the temperature of the chilled water. The frequency is reduced at low loads and increased at high loads to ensure that the water pump operates in the optimal energy efficiency range. Specifically, based on the solved value of the load of the air-conditioning chiller system, the corresponding chilled water outlet temperature, chilled water flow rate, chilled water flow velocity, etc. can be deduced. Then, the water pump outlet pressure can be determined according to the chilled water outlet temperature, chilled water flow rate (water pump outlet flow rate), chilled water flow velocity, etc. Then, based on the water pump outlet pressure and the water pump outlet flow rate, the operating frequency of the water pump under the condition of the minimum water pump power at a predicted load of a certain air-conditioning chiller system can be determined.

[0169] Minimum operating frequency setting: When the demand is low, the minimum operating frequency of the water pump is set to maintain the basic flow rate of the system and avoid vibration and damage during low-frequency operation of the water pump.

[0170] The adjustment end condition is: until the difference between the solved value of the load of the air-conditioning chiller system and the current value of the load of the air-conditioning system chiller, or the difference between the current value of the load of the air-conditioning system chiller and the solved value of the load of the air-conditioning chiller system is not greater than the second preset threshold, where the second preset threshold is less than the first preset threshold. Specifically, the first preset threshold can be the refrigerating capacity (load) of a single chiller + a custom value, and the second preset threshold can be the refrigerating capacity (load) of a single chiller - a custom value; among them, the custom value can be flexibly adjusted according to the actual situation, and this embodiment does not limit it here.

[0171] Functions of the intelligent controller (running the chiller optimization control method):

[0172] Real-time data acquisition: Real-time obtain data such as temperature, humidity, number of people, equipment status, etc. as the basis for decision-making.

[0173] Dynamic adjustment: Automatically adjust system parameters such as chillers, water pumps, and outlet temperature according to environmental changes and demand changes to ensure the maximum energy efficiency of chiller operation.

[0174] Fault detection and prediction: Through continuous monitoring of the operating status of the equipment, the intelligent controller can detect equipment faults and provide predictive maintenance suggestions to reduce the equipment failure rate.

[0175] Integration of optimization algorithms

[0176] Combined with machine learning, deep learning, fuzzy control or adaptive control algorithms to enhance the dynamic adjustment ability of the chiller system. Adjust the strategy in real time according to environmental changes to avoid the inefficiency problems caused by static preset parameters.

[0177] Implementation of optimization algorithms:

[0178] Machine learning, deep learning: The intelligent controller continuously learns and optimizes operation strategies such as the start and stop of the chiller, the adjustment of the water pump frequency, and the adjustment of the outlet water temperature through machine learning and deep learning algorithms.

[0179] Fuzzy control: According to multi-dimensional factors such as temperature, humidity, and load, the chiller parameters are adjusted in real time through fuzzy control rules, making the adjustment smoother and more accurate.

[0180] Adaptive control: Combining adaptive control algorithms, the control parameters of the system are automatically adjusted according to real-time monitoring data to ensure that the system always operates efficiently under different working environments.

[0181] Real-time monitoring and feedback module:

[0182] Real-time monitor the operating status of the chiller system, and adjust the control strategy through the feedback mechanism to ensure that the system always operates in the optimal state.

[0183] Regularly conduct system self-checks to detect whether the chiller has failures, and timely remind the maintenance personnel to conduct inspections and maintenance.

[0184] Based on the historical data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, and the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, the present invention establishes a load prediction model and a human comfort model for the air-conditioning chiller system; with the minimization of the sum of the load of the air-conditioning chiller system and human comfort as the optimization goal, a multi-objective optimization algorithm is established, wherein the weights of the load of the air-conditioning chiller system and human comfort can be adjusted according to the real-time data of the internal and external environments of the high-speed railway station; solve the multi-objective optimization algorithm, and conduct chiller optimization control according to the solved value of the load of the air-conditioning chiller system and the current value of the load of the air-conditioning chiller system, effectively solving the problem of low reliability of the multi-objective optimization of energy conservation and carbon reduction of the cold source system in high-speed railway stations caused by the existing technology, and effectively improving the reliability of the multi-objective optimization of energy conservation and carbon reduction of the cold source system in high-speed railway stations.

[0185] In the technical solution of the present invention, the weights of the load of the air-conditioning chiller system and human comfort can be adjusted according to the real-time data of the internal and external environments of the high-speed railway station, which not only considers the internal and external environmental factors of the high-speed railway station, but also considers the current passenger flow inside the high-speed railway station, further improving the reliability of the multi-objective optimization of energy conservation and carbon reduction of the cold source system in high-speed railway stations.

[0186] In the technical solution of the present invention, when selecting a solved value of the load of a certain air-conditioning chiller system, the chiller combination with the highest operating efficiency in the current air-conditioning chiller system is selected for operation. If a certain chiller is in the chiller combination and the current on-off state of the chiller is off, then select the chiller to turn on; if a certain chiller is not in the chiller combination and the current on-off state of the chiller is on, then select the chiller to turn off, ensuring the operating efficiency of the chiller in the air-conditioning system.

[0187] In the technical solution of the present invention, when the solved value of the air-conditioning chiller system load is greater than the current value of the air-conditioning system chiller load, and the difference between the solved value of the air-conditioning chiller system load and the current value of the air-conditioning system chiller load is not greater than the first preset threshold, the operating frequency of the water pump is increased, or the chiller outlet water temperature is decreased; when the solved value of the air-conditioning chiller system load is less than the current value of the air-conditioning system chiller load, and the difference between the current value of the chiller load and the solved value of the chiller load is not greater than the first preset threshold, the operating frequency of the water pump is decreased, or the chiller outlet water temperature is increased, ensuring the applicability of the optimized control of the chiller in the cold source system of the high-speed railway station.

[0188] Embodiment 2

[0189] As Figure 7 shown, the technical solution of the present invention also provides an energy-saving and carbon-reducing multi-objective optimization device for the cold source system of a high-speed railway station, including:

[0190] An acquisition module 101, which acquires the historical data of the air-conditioning chiller system including timestamp information, the real-time data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, the real-time data of the internal and external environments of the high-speed railway station, the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, and the real-time data of the thermal comfort evaluation of the internal environment of the high-speed railway station;

[0191] A first establishment module 102, which establishes an air-conditioning chiller system load prediction model and a human comfort model based on the historical data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, and the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station; <urchin>

[0192] A second establishment module 103, which establishes a multi-objective optimization algorithm with the minimization of the sum of the air-conditioning chiller system load and human comfort as the optimization goal, wherein the weights of the air-conditioning chiller system load and human comfort can be adjusted according to the real-time data of the internal and external environments of the high-speed railway station;

[0193] An optimization control module 104, which solves the multi-objective optimization algorithm and performs optimized control of the chiller according to the solved value of the air-conditioning chiller system load and the current value of the air-conditioning chiller system load.

[0194] It should be noted that the implementation processes of the acquisition module 101, the first establishment module 102, the second establishment module 103, and the optimization control module 104 in the embodiments of the present invention correspond to the execution steps of the method in Embodiment 1, and will not be elaborated herein.

[0195] Based on the historical data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, and the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, the present invention establishes a load prediction model for the air-conditioning chiller system and a human comfort model; taking the minimization of the sum of the load of the air-conditioning chiller system and human comfort as the optimization objective, a multi-objective optimization algorithm is established, wherein the weights of the load of the air-conditioning chiller system and human comfort can be adjusted according to the real-time data of the internal and external environments of the high-speed railway station; solving the multi-objective optimization algorithm, and performing chiller optimization control according to the solved value of the load of the air-conditioning chiller system and the current value of the load of the air-conditioning chiller system, effectively solving the problem of low reliability of the multi-objective optimization of energy conservation and carbon reduction of the cold source system in the high-speed railway station caused by the existing technology, and effectively improving the reliability of the multi-objective optimization of energy conservation and carbon reduction of the cold source system in the high-speed railway station.

[0196] In the technical solution of the present invention, the weights of the load of the air-conditioning chiller system and human comfort can be adjusted according to the real-time data of the internal and external environments of the high-speed railway station, which not only considers the internal and external environmental factors of the high-speed railway station, but also considers the current passenger flow inside the high-speed railway station, further improving the reliability of the multi-objective optimization of energy conservation and carbon reduction of the cold source system in the high-speed railway station.

[0197] In the technical solution of the present invention, when a certain solved value of the load of the air-conditioning chiller system is selected, the chiller combination with the highest operating efficiency in the current chiller system of the air-conditioning chiller system is selected for operation. If a certain chiller is in the chiller combination and the current operating state of the chiller is off, then the chiller is selected to be turned on; if a certain chiller is not in the chiller combination and the current operating state of the chiller is on, then the chiller is selected to be turned off, ensuring the operating efficiency of the chiller in the air-conditioning system.

[0198] In the technical solution of the present invention, when the solved value of the load of the air-conditioning chiller system is greater than the current value of the load of the chiller in the air-conditioning system, and the difference between the solved value of the load of the air-conditioning chiller system and the current value of the load of the chiller in the air-conditioning system is not greater than the first preset threshold, the operating frequency of the water pump is increased, or the outlet water temperature of the chiller is decreased; when the solved value of the load of the air-conditioning chiller system is less than the current value of the load of the chiller in the air-conditioning system, and the difference between the current value of the load of the chiller and the solved value of the load of the chiller is not greater than the first preset threshold, the operating frequency of the water pump is decreased, or the outlet water temperature of the chiller is increased, ensuring the applicability of the chiller optimization control in the cold source system of the high-speed railway station.

[0199] Although the specific implementation manners of the present invention are described above in conjunction with the accompanying drawings, it is not a limitation to the protection scope of the present invention. Those skilled in the art should understand that based on the technical solution of the present invention, various modifications or deformations that can be made by those skilled in the art without creative labor are still within the protection scope of the present invention.

Claims

1. An energy-saving and carbon-reducing multi-objective optimization method for the cold source system of a high-speed railway station, characterized in that, Including: Obtain the historical data of the air-conditioning chiller system including timestamp information, the real-time data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, the real-time data of the internal and external environments of the high-speed railway station, the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, and the real-time data of the thermal comfort evaluation of the internal environment of the high-speed railway station; Based on the historical data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, and the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, establish an air-conditioning chiller system load prediction model and a human comfort model; Taking the minimization of the sum of the air-conditioning chiller system load and human comfort as the optimization goal, establish a multi-objective optimization algorithm, where the weights of the air-conditioning chiller system load and human comfort can be adjusted according to the real-time data of the internal and external environments of the high-speed railway station; Solve the multi-objective optimization algorithm, and perform chiller optimization control according to the solved value of the air-conditioning chiller system load and the current value of the air-conditioning chiller system load.

2. The energy-saving and carbon-reducing multi-objective optimization method for the cold source system of a high-speed railway station according to claim 1, characterized in that, Based on the historical data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, and the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, establishing an air-conditioning chiller system load prediction model and a human comfort model specifically includes: Taking the air-conditioning chiller system load as the output and the historical data of the internal and external environments of the high-speed railway station as the input, based on the historical data of the air-conditioning chiller system and the historical data of the internal and external environments of the high-speed railway station, establish and train an LSTM time series model to predict the future load of the air-conditioning chiller system; Taking the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station as the output and the historical data of the internal and external environments of the high-speed railway station as the input, based on the historical data of the air-conditioning chiller system and the historical data of the internal and external environments of the high-speed railway station, establish and train a PMV model based on different time periods to predict the thermal comfort under a certain set of internal and external environment data of the high-speed railway station at different time periods.

3. The energy-saving and carbon-reducing multi-objective optimization method for the cold source system of a high-speed railway station according to claim 1, wherein, The objective function of the multi-objective optimization algorithm is specifically: min(w1(t)·E ac (t)+w2(t)·Deviations from Comfort(t)) where, w1(t) is the weight of the energy-saving target at time t, and E ac (t) is the energy consumption of the air-conditioning chiller system at time t, w2(t) is the weight of the thermal comfort target at time t, and Deviations from Comfort(t) is the thermal comfort at time t.

4. The energy-saving and carbon-emission-reducing multi-objective optimization method for the cold source system of a high-speed railway station according to claim 3, wherein, The weights of the air-conditioning chiller system load and human comfort can be adjusted according to the real-time data of the internal and external environments of the high-speed railway station specifically as: w2(t) = α0·e PMV(t)·N(t) Among them, α0 is the initial weight of thermal comfort, PMV(t) is the PMV value under the internal and external environment data of the high-speed railway station at the current moment t, and N(t) is the current passenger flow in the high-speed railway station; w1(t) = 1 - w2(t) Among them, w1(t) is the weight of the air-conditioning chiller system load.

5. A method for multi-objective optimization of energy conservation and carbon reduction in a cold source system of a high-speed railway station according to claim 1, characterized in that Solving the multi-objective optimization algorithm and performing chiller optimization control according to the solved value of the air-conditioning chiller system load and the current value of the air-conditioning chiller system load specifically includes: Solve the air-conditioning chiller system load corresponding to the minimum of the objective function. When the solved value of the air-conditioning chiller system load is greater than the current value of the air-conditioning system chiller load, and the difference between the solved value of the air-conditioning chiller system load and the current value of the air-conditioning system chiller load is greater than the first preset threshold, select to turn on some chillers; when the solved value of the air-conditioning chiller system load is less than the current value of the air-conditioning system chiller load, and the difference between the current value of the chiller load and the solved value of the chiller load is greater than the first preset threshold, select to turn off some chillers.

6. The energy-saving and carbon-emission-reducing multi-objective optimization method for the cold source system of a high-speed railway station according to claim 5, characterized in that Selecting to turn on or off some chillers specifically is: Obtain the corresponding relationship between different solved values of the air-conditioning chiller system load and the operating efficiency of the chiller system under any combination of all chillers in the current air-conditioning chiller system; When selecting the combination of chillers with the highest operating efficiency in the current chiller system at a certain load solution value of the air-conditioning chiller system, if a certain chiller is in this chiller combination and its current operating state is off, then select to turn on this chiller; if a certain chiller is not in this chiller combination and its current operating state is on, then select to turn off this chiller.

7. A multi-objective optimization method for energy conservation and carbon reduction of a cold source system in a high-speed railway station according to claim 1, characterized in that Before establishing a multi-objective optimization algorithm with the minimization of the sum of the air-conditioning chiller system load and human comfort as the optimization objective, it also includes: Obtain the historical data of the water pumps in the air-conditioning chiller system and the real-time data of the water pumps in the air-conditioning chiller system, including timestamp information; Based on the historical data of the water pumps in the air-conditioning chiller system and the real-time data of the water pumps in the air-conditioning chiller system, with the power of the water pumps in the air-conditioning chiller system as the output and the historical data of the operating frequency of the water pumps, the historical data of the water outlet pressure of the water pumps, and the historical data of the water outlet flow of the water pumps as the input, establish and train a prediction model for the power consumption of the water pumps to predict the power of the water pumps under a certain air-conditioning chiller system load.

8. A multi-objective optimization method for energy conservation and carbon reduction of a cold source system in a high-speed railway station according to claim 7 or 5, characterized in that Solve the multi-objective optimization algorithm, and perform chiller optimization control according to the load solution value of the air-conditioning chiller system and the current value of the air-conditioning chiller system load, which specifically includes: Solve the air-conditioning chiller system load corresponding to the minimum of the objective function. When the load solution value of the air-conditioning chiller system is greater than the current value of the air-conditioning system chiller load, and the difference between the load solution value of the air-conditioning chiller system and the current value of the air-conditioning system chiller load is not greater than the first preset threshold, increase the operating frequency of the water pumps or lower the chilled water outlet temperature; when the load solution value of the air-conditioning chiller system is less than the current value of the air-conditioning system chiller load, and the difference between the current value of the chiller load and the load solution value of the chiller is not greater than the first preset threshold, decrease the operating frequency of the water pumps or increase the chilled water outlet temperature.

9. A method for multi-objective optimization of energy conservation and carbon reduction in the cold source system of a high-speed railway station according to claim 8, characterized in that, Until the difference between the load solution value of the air-conditioning chiller system and the current value of the air-conditioning system chiller load, or the difference between the current value of the air-conditioning chiller system load and the load solution value of the air-conditioning system chiller is not greater than the second preset threshold, where the second preset threshold is less than the first preset threshold.

10. An energy-saving, carbon-reducing, multi-objective optimization device for the cold source system of a high-speed railway station, characterized in that, It includes: An acquisition module that acquires the historical data of the air-conditioning chiller system, the real-time data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, the real-time data of the internal and external environments of the high-speed railway station, the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station, and the real-time data of the thermal comfort evaluation of the internal environment of the high-speed railway station, including timestamp information; A first establishment module that establishes an air-conditioning chiller system load prediction model and a human comfort model based on the historical data of the air-conditioning chiller system, the historical data of the internal and external environments of the high-speed railway station, and the historical data of the thermal comfort evaluation of the internal environment of the high-speed railway station; A second establishment module that establishes a multi-objective optimization algorithm with the minimization of the sum of the air-conditioning chiller system load and human comfort as the optimization objective, where the weights of the air-conditioning chiller system load and human comfort can be adjusted according to the real-time data of the internal and external environments of the high-speed railway station; An optimization control module that solves the multi-objective optimization algorithm and performs chiller optimization control according to the load solution value of the air-conditioning chiller system and the current value of the air-conditioning chiller system load.

Images