Optimized operation method of air source heat pump-fan coil central air-conditioning system

Abstract

The invention belongs to the technical field of optimized operation of central air-conditioning systems, and particularly discloses an optimized operation method of an air source heat pump-fan coil central air-conditioning system, which comprises the following steps of: firstly, acquiring influence factors of building load and outdoor meteorological parameters; a central air conditioner load prediction model, an outdoor meteorological parameter prediction model and a data driving model of an air source heat pump and a water pump are constructed, the total energy consumption of system operation, the load demand at the next moment, the outdoor environment temperature and the outdoor relative humidity are obtained through prediction, and then an optimization objective function and constraint conditions are set; and solving the optimization objective function and the constraint condition by using a grid search optimization algorithm to obtain the set temperature of the host at the next moment and the set frequency of the water pump at the next moment, and completing the optimization process. According to the method, the problem of high hysteresis of the central air-conditioning water system is solved, and the host set temperature and the water pump set frequency at the next moment are optimized and solved according to the operation data at the current moment.

Description

Technical Field

[0001] The present invention belongs to the technical field of optimized operation of air-conditioning systems, and in particular relates to an optimized operation method of an air source heat pump-fan coil central air-conditioning system. Background Art

[0002] The actual operating status of each device in the central air-conditioning system is affected by factors such as outdoor environmental parameters and end-user needs. If the optimal operating status point cannot be found, it will affect the equipment's operating energy consumption and even cause indoor thermal comfort to fail to meet requirements. However, existing air-conditioning systems have problems such as over-sized equipment and low equipment utilization. The system still has a lot of room for energy-saving optimization. Therefore, finding the optimal operating status of the equipment under different outdoor meteorological parameters and load requirements is of great significance to achieving the optimal operation of the central air-conditioning system. Existing research on the optimal operation of central air-conditioning hot and cold water systems mainly focuses on two aspects: optimal control of the number of units and optimal control of set parameters.

[0003] There are two main modes for optimal control of the number of units. One is start-stop control, which is to start the operating number of the main unit, water pump, cooling tower and other equipment one by one according to the load demand on the user side. When a single device cannot meet the user's environmental requirements, additional equipment is turned on for cooling or heating. The other is load distribution control, which is to start multiple devices at the same time and distribute cooling and heating capacity according to the equipment performance, so as to solve the optimal load distribution state of each device.

[0004] In order to solve the problem of strong coupling of central air-conditioning system, this paper mainly studies the optimal operation strategy of hot and cold water system. The parameter optimization control is set to calculate the parameter combination with the lowest energy consumption of central air-conditioning system under the premise of meeting the indoor load demand. The optimization path mainly has three steps: establishing equipment model, setting constraint range and finally optimizing the solution.

[0005] In addition, the development of computer theory has provided technical support for the control of central air-conditioning systems. The adjustment of chilled water system parameters no longer relies on local control, but adopts PID control. However, traditional PID adjustment is difficult to handle the complex coupling relationship between variables and to achieve system optimization control. Moreover, this control method belongs to feedback control. When it is found that the energy efficiency of the equipment or the indoor thermal comfort does not meet the set requirements, it is too late to adjust the operating parameters of the host or water pump. It is difficult to give full play to its advantages for chilled water systems with strong hysteresis. Summary of the invention

[0006] The purpose of the present invention is to solve the problem of strong hysteresis of the central air-conditioning water system, and proposes an optimized operation method for an air source heat pump-fan coil central air-conditioning system.

[0007] The technical solution of the present invention is: an optimized operation method of an air source heat pump-fan coil central air conditioning system, comprising the following steps:

[0008] S1. Obtain the influencing factors of building load and outdoor meteorological parameters;

[0009] S2. Construct a central air conditioning load prediction model and an outdoor meteorological parameter prediction model based on the influencing factors, and predict the load demand Q at the next moment. t+1 , the outdoor ambient temperature Tdb at the next moment t+1 and the outdoor relative humidity RH at the next moment t+1 ;

[0010] S3. Determine the main influencing factors of the operating performance of the air source heat pump and the water pump, build a data-driven model of the air source heat pump and the water pump, and perform simulation operation based on the data-driven model to obtain the total energy consumption of the central air-conditioning system;

[0011] S4. Based on the total energy consumption of the central air-conditioning system and the load demand Q at the next moment t+1 , the outdoor ambient temperature Tdb at the next moment t+1 and the outdoor relative humidity RH at the next moment t+1 Based on the prediction results, set the optimization objective function and constraints;

[0012] S5. Use the grid search optimization algorithm to solve the optimization objective function and constraints to obtain the host set temperature Tset at the next moment t+1 And the pump setting frequency Nset at the next moment t+1 , completing the optimization process.

[0013] The beneficial effects of the present invention are:

[0014] The present invention aims at the characteristics of system complexity, coupling and strong hysteresis, establishes a prediction model and an equipment model, and realizes the optimization solution of the load demand, host setting temperature and water pump setting frequency at the next moment according to the operation data at the current moment, thereby improving the system operation efficiency and reducing the operation energy consumption.

[0015] Preferably, the step S2 specifically comprises the following steps:

[0016] S21. Perform normalization processing on the influencing factors, and the formula for the normalization processing is:

[0017]

[0018] Among them, v' is the value after normalization, v is the value before normalization, and v max is the maximum value of the parameter before normalization, v minis the minimum value of the parameter before normalization;

[0019] S22. Calculate the correlation coefficient between the normalized influencing factors and the cooling and heating loads. The calculation formula of the correlation coefficient is:

[0020]

[0021] Among them, r p is the correlation coefficient, q is the number of influencing factors, X s is the sth influencing factor, is the average value of the influencing factors, Y s is the sth building load, is the average value of the building load;

[0022] S23. Determine the input parameters and output parameters of the XGBoost model according to the correlation coefficient, set the hyperparameters of the XGBoost model, and train the XGBoost model;

[0023] S24. Optimize the trained XGBoost model using the sparrow search algorithm to obtain a central air conditioning load prediction model and an outdoor meteorological parameter prediction model;

[0024] S25. Input the current time t, date, outdoor dry-bulb temperature at time t, outdoor wet-bulb temperature at time t and building load at time t into the central air-conditioning load prediction model to obtain the output data of the central air-conditioning load prediction model;

[0025] S26. Input the outdoor dry-bulb temperature at the current time t, the outdoor dry-bulb temperature at the time t, and the outdoor wet-bulb temperature at the time t into the outdoor meteorological parameter prediction model to obtain the output data of the outdoor meteorological parameter prediction model;

[0026] S27. Denormalize the output data of the central air conditioning load prediction model to obtain the load demand Q at the next moment. t+1 , and the output data of the outdoor meteorological parameter prediction model is denormalized to obtain the outdoor ambient temperature Tdb at the next moment t+1 and the outdoor relative humidity RH at the next moment t+1 ; The formula for the denormalization process is:

[0027] y=y'·(y max -y min )+y min

[0028] Among them, y is the value of the output data after denormalization, y' is the value of the output data before denormalization, and y max is the maximum value before load normalization in the training data, y minis the minimum value of the load in the training data before normalization.

[0029] Preferably, the objective function of the XGBoost model during training is:

[0030]

[0031] Among them, Obj is the objective function of the XGBoost model, I j is the set of all samples belonging to leaf node j, g l is the first-order partial derivative of the lth sample in leaf node j, h l is the second-order partial derivative of the lth sample in leaf node j, λ is the regularization parameter, n is the total number of training data samples, γT is the regularization coefficient, γ is the adjustment coefficient, and T is the number of leaf nodes in the tree.

[0032] The beneficial effects of the above preferred solution are:

[0033] This preferred solution adopts the XGBoost model to construct a central air-conditioning load prediction model and an outdoor meteorological parameter prediction model, and considers the current time t, date, outdoor dry-bulb temperature at time t, outdoor wet-bulb temperature at time t and building load at time t as input parameters of the central air-conditioning load prediction model. This avoids the situation where the load value at the next moment has a large difference due to the strong heat storage capacity of the building itself and the large changes in indoor thermal disturbance, thereby improving the prediction accuracy.

[0034] Preferably, the data-driven models of the air source heat pump and the water pump in step S3 include an air source hot water pump model and a water pump model.

[0035] Preferably, the objective function in step S4 is the total energy consumption of the system operation at the next moment, and the specific expression formula is:

[0036] P total(t+1) =P ashp(t+1) +P pump(t+1)

[0037] =f 1 (Tdb (t+1) ,RH (t+1) ,Tset (t+1) ,Nset (t+1) ,Q (t+1) )+f 3 (Nset (t+1) )

[0038] Among them, P total(t+1) is the total energy consumption of the central air-conditioning system at time t+1, kW, P ashp(t+1) is the operating energy consumption of the heat pump at time t+1, kW, P pump(t+1)is the operating energy consumption of the pump at time t+1, kW, Tdb (t+1) is the outdoor dry-bulb temperature at time t+1, °C, RH (t+1) is the outdoor relative humidity at time t+1, %, Tset (t+1) Set the host temperature at time t+1, ℃, Nset (t+1) is the pump set frequency at time t+1, Q (t+1) is the load demand at time t+1, kW, f 1 (·) indicates parameter Tdb (t+1) RH (t+1) 、Tset (t+1) 、Nset (t+1) and Q (t+1) The functional relationship with the host is obtained from the air source hot water pump model, f 3 (·) indicates parameter Nset (t+1) The functional relationship with the water pump is obtained from the water pump model.

[0039] Preferably, the constraints in step S4 include a host setting temperature constraint, a water pump setting frequency constraint and an indoor thermal comfort constraint; the indoor thermal comfort constraint is the maximum heat exchange capacity of the terminal.

[0040] Preferably, the host setting temperature constraint is specifically:

[0041]

[0042] Among them, Tset (t+1) Set the host temperature at time t+1.

[0043] Preferably, the water pump setting frequency constraint is specifically:

[0044] 30Hz≤Nset (t+1) ≤50Hz

[0045] Among them, Nset (t+1) Set the frequency of the pump at time t+1.

[0046] Preferably, the calculation formula for the maximum heat exchange capacity of the terminal is:

[0047]

[0048] Among them, y totalc is the sum of the summer heat transfer capacity of all fan coil units, that is, the maximum heat transfer capacity at the end of summer, y totalh is the sum of the heat transfer capacity of all fan coil units in winter, that is, the maximum heat transfer capacity at the end of winter, p is the number of fan coil units of different models, y ic is the summer heat exchange capacity of a single fan coil unit, y ihis the winter heat exchange capacity of a single fan coil unit, k ic is the slope of the summer heat transfer capacity equation, k ih is the slope of the winter heat transfer capacity equation, u is the water supply temperature, b ic is the intercept in summer heat transfer capacity, b ih is the intercept in winter heat transfer capacity, k totalc is the slope of the maximum heat transfer capacity equation at the end of summer, k totalh is the slope of the maximum heat transfer capacity equation at the end of winter, b totalc is the intercept of the maximum heat transfer capacity at the end of summer, b totalh is the intercept of the maximum heat exchange capacity at the terminal in winter, i is the total number of fan coil types, i∈[1,7], g and a represent the maximum and minimum number of different models, respectively.

[0049] In this preferred solution, the sum of the host energy consumption and the water pump energy consumption at the next moment is used as the optimization objective function, and the host set temperature, water pump set frequency and terminal maximum heat exchange capacity are used as constraints, which improves the system operation efficiency and reduces the operation energy consumption.

[0050] Preferably, the step S5 specifically comprises the following steps:

[0051] S51. Set the optimization step and optimization interval of the host set temperature and the water pump set frequency respectively;

[0052] S52. Set the parameter grid and traverse all grid nodes according to the optimization step size and optimization interval;

[0053] S53. Count all nodes whose heat exchange capacity meets the load demand, and substitute all nodes into the objective function to calculate, and obtain the node corresponding to the minimum objective function, which is the host set temperature Tset at the next moment. t+1 And the pump setting frequency Nset at the next moment t+1 The optimal combination of

[0054] The beneficial effects of the above preferred solution are:

[0055] When the grid search optimization algorithm solves the optimization objective function and constraints, it systematically traverses all possible combinations in the parameter space through an exhaustive method, which can ensure that all potential optimal solutions are found within a limited time, and accurately solve the optimization objective function and constraints, effectively improving the system operation efficiency and reducing the operation energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 Shown is a flow chart of an optimized operation method for an air source heat pump-fan coil central air conditioning system.

[0057] Figure 2 Shown is a schematic diagram of energy consumption analysis after optimization of summer operating condition 1 provided in Example 2 of the present invention.

[0058] Figure 3 Shown is a schematic diagram of energy consumption analysis after optimization of summer operating condition 2 provided in Example 2 of the present invention.

[0059] Figure 4 The figure shows a schematic diagram of energy consumption analysis after optimization of summer operating condition 3 provided in Example 2 of the present invention.

[0060] Figure 5 The figure shows a schematic diagram of energy consumption analysis after optimization of summer operating condition 4 provided in Example 2 of the present invention.

[0061] Figure 6 Shown is a schematic diagram of energy consumption analysis after optimization of winter operating condition 1 provided in Example 2 of the present invention.

[0062] Figure 7 Shown is a schematic diagram of energy consumption analysis after optimization of winter operating condition 2 provided in Example 2 of the present invention.

[0063] Figure 8 Shown is a schematic diagram of energy consumption analysis after optimization of winter operating condition 3 provided in Example 2 of the present invention.

[0064] Fig. 9 Shown is a schematic diagram of energy consumption analysis after optimization of winter operating condition 4 provided in Example 2 of the present invention.

[0065] Fig.10 Shown is a diagram of the summer optimization results provided in Example 3 of the present invention.

[0066] Fig.11 Shown is a diagram of winter optimization results provided in Example 3 of the present invention.

[0067] Fig.12 Shown is a graph comparing energy consumption before and after summer optimization provided in Example 3 of the present invention.

[0068] Fig.13 Shown is a diagram comparing the energy consumption before and after winter optimization provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0069] Now, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be understood that the embodiments shown and described in the accompanying drawings are only exemplary and are intended to explain the principles and spirit of the present invention, rather than to limit the scope of the present invention.

[0070] Embodiment 1:

[0071] like Figure 1 As shown, an optimized operation method of an air source heat pump-fan coil central air conditioning system comprises the following steps:

[0072] S1. Obtain the influencing factors of building load and outdoor meteorological parameters;

[0073] S2. Construct a central air conditioning load prediction model and an outdoor meteorological parameter prediction model based on the influencing factors, and predict the load demand Q at the next moment. t+1 , the outdoor ambient temperature Tdb at the next moment t+1 and the outdoor relative humidity RH at the next moment t+1 ;

[0074] S3. Determine the main influencing factors of the operating performance of air source heat pumps and water pumps, build data-driven models of air source heat pumps and water pumps, and use the Type155 component in the TRNSYS software based on the data-driven model to simulate the operating energy consumption of the cooling season and heating season throughout the year to obtain the total operating energy consumption of the central air-conditioning system, where the set temperature of the chilled water is 10°C, the water pump frequency is 50Hz, and the set temperature of the hot water in winter is 42°C, and the water pump frequency is 50Hz;

[0075] S4. Based on the total energy consumption of the central air-conditioning system and the load demand Q at the next moment t+1 , the outdoor ambient temperature Tdb at the next moment t+1 and the outdoor relative humidity RH at the next moment t+1 Based on the prediction results, set the optimization objective function and constraints;

[0076] S5. Use the grid search optimization algorithm to solve the optimization objective function and constraints to obtain the host set temperature Tset at the next moment t+1 And the pump setting frequency Nset at the next moment t+1 , completing the optimization process.

[0077] In this embodiment, step S2 specifically includes the following steps:

[0078] S21. Perform normalization processing on the influencing factors, and the formula for the normalization processing is:

[0079]

[0080] Among them, v' is the value after normalization, v is the value before normalization, and v max is the maximum value of the parameter before normalization, v min is the minimum value of the parameter before normalization;

[0081] S22. Calculate the correlation coefficient between the normalized influencing factors and the cooling and heating loads. The calculation formula of the correlation coefficient is:

[0082]

[0083] Among them, r p is the correlation coefficient, q is the number of influencing factors, X s is the sth influencing factor, is the average value of the influencing factors, Y s is the sth building load, is the average value of the building load;

[0084] S23. Determine the input parameters and output parameters of the XGBoost model according to the correlation coefficient, set the hyperparameters of the XGBoost model, and train the XGBoost model; the hyperparameters include: maximum tree depth (max depth), learning rate (learning rate), minimum node weight (min child weight), base learning tree data set ratio (subsample), the number of base learning trees (n_estimators), base learning tree feature ratio (colsample) and regularization coefficient γT;

[0085] The maximum tree depth represents the maximum number of layers that can be achieved when a single decision tree is learned. The greater the tree depth, the more the model can reflect the complex relationship between the features, but the calculation time will be longer, and overfitting is prone to occur. However, if the tree depth is too small, the accuracy of the model will be reduced, so it is set to 6.

[0086] The larger the learning rate setting value, the greater the weight given to the decision tree, but it is easy to cause model instability; the lower the setting value, the lower the calculation speed will be, which will suppress the weight of each tree in the entire model, so the value is set to 0.3;

[0087] The minimum node weight represents the minimum number of samples in each node. When the number of samples in the node is less than this value, the decision tree will stop splitting. Similarly, the larger the value, the easier it is to cause under-fitting of the model, and too small a value will easily lead to over-fitting, so this value is set to 1.

[0088] The base learning tree dataset ratio controls the random sampling ratio of each tree, so this value is set to 1;

[0089] The number of base learning trees represents the number of generated decision trees, also known as the number of iterations, which is set to 50;

[0090] The base learning tree feature ratio is the ratio of sample features selected by each decision tree, and the value is set to 1;

[0091] The default value of the regularization coefficient γT is set to 1;

[0092] S24. The maximum tree depth, the number of base learning trees and the learning rate in the trained XGBoost model hyperparameters are optimized using the sparrow search algorithm, and the optimization ranges are [1,50], [1,200] and [0.01,0.3], respectively, to obtain the central air conditioning load prediction model and the outdoor meteorological parameter prediction model;

[0093] The central air conditioning load prediction model is divided into a summer cooling load prediction model and a winter heating load prediction model; the maximum tree depth, the number of base learning trees and the learning rate of the summer cooling load prediction model are 5, 143 and 0.0955 respectively; the maximum tree depth, the number of base learning trees and the learning rate of the winter heating load prediction model are 6, 121 and 0.124 respectively;

[0094] The outdoor meteorological parameter prediction model is divided into a summer outdoor meteorological parameter prediction model and a winter outdoor meteorological parameter prediction model; the maximum tree depth, the number of base learning trees and the learning rate of the outdoor dry-bulb temperature of the summer outdoor meteorological parameter prediction model are 42, 200 and 0.29 respectively, and the maximum tree depth, the number of base learning trees and the learning rate of the outdoor relative humidity are 48, 193 and 0.2758 respectively; the maximum tree depth, the number of base learning trees and the learning rate of the outdoor dry-bulb temperature of the winter outdoor meteorological parameter prediction model are 29, 124 and 0.2466 respectively, and the maximum tree depth, the number of base learning trees and the learning rate of the outdoor relative humidity are 35, 139 and 0.2105 respectively;

[0095] S25. Input the current time t, date, outdoor dry-bulb temperature at time t, outdoor wet-bulb temperature at time t and building load at time t into the central air-conditioning load prediction model to obtain the output data of the central air-conditioning load prediction model;

[0096] S26. Input the outdoor dry-bulb temperature at the current time t, the outdoor dry-bulb temperature at the time t, and the outdoor wet-bulb temperature at the time t into the outdoor meteorological parameter prediction model to obtain the output data of the outdoor meteorological parameter prediction model;

[0097] S27. Denormalize the output data of the central air conditioning load prediction model to obtain the load demand Q at the next moment. t+1 , and the output data of the outdoor meteorological parameter prediction model is denormalized to obtain the outdoor ambient temperature Tdb at the next moment t+1 and the outdoor relative humidity RH at the next moment t+1 ; The formula for the denormalization process is:

[0098] y=y'·(y max -y min )+y min

[0099] Among them, y is the value of the output data after denormalization, y' is the value of the output data before denormalization, and y max is the maximum value before load normalization in the training data, y min is the minimum value of the load in the training data before normalization.

[0100] In this embodiment, when the XGBoost model is trained in step S23, multiple decision trees are constructed in sequence in a serial manner. When each tree is trained, the model parameters of the tree are determined in combination with the prediction results of the previous tree. Through continuous iteration, accurate prediction results are obtained. At the same time, in each iteration, the prediction weights of the erroneous samples are assigned with the help of the gradient descent method, so that the iterative error of each round is smaller than that of the previous round. The objective function of the XGBoost model in the training process is:

[0101]

[0102] Among them, Obj is the objective function of the XGBoost model, I j is the set of all samples belonging to leaf node j, g l is the first-order partial derivative of the lth sample in leaf node j, h l is the second-order partial derivative of the lth sample in leaf node j, λ is the regularization parameter, n is the total number of training data samples, γT is the regularization coefficient, γ is the adjustment coefficient, and T is the number of leaf nodes in the tree.

[0103] In this embodiment, the data-driven models of the air source heat pump and the water pump in step S3 include an air source hot water pump model and a water pump model.

[0104] In this embodiment, the main purpose of optimization is to reduce the total energy consumption of the air conditioning water system. The purpose of this embodiment is to solve the optimal host setting temperature and water pump setting frequency at the next time t+1 according to the operating parameters at the current time t. Therefore, the objective function in step S4 is the total energy consumption of the system operation at the next time. The specific expression formula is:

[0105] P total(t+1) =P ashp(t+1) +P pump(t+1)

[0106] =f 1 (Tdb (t+1) ,RH (t+1) ,Tset (t+1) ,Nset (t+1) ,Q (t+1) )+f 3 (Nset (t+1) )

[0107] Among them, Ptotal(t+1) is the total energy consumption of the central air-conditioning system at time t+1, kW, P ashp(t+1) is the operating energy consumption of the heat pump at time t+1, kW, P pump(t+1) is the operating energy consumption of the pump at time t+1, kW, Tdb (t+1) is the outdoor dry-bulb temperature at time t+1, °C, RH (t+1) is the outdoor relative humidity at time t+1, %, Tset (t+1) Set the host temperature at time t+1, ℃, Nset (t+1) is the pump set frequency at time t+1, Q (t+1) is the load demand at time t+1, kW, f 1 (·) indicates parameter Tdb (t+1) RH (t+1) 、Tset (t+1) 、Nset (t+1) and Q (t+1) The functional relationship with the host is obtained from the air source hot water pump model, f 3 (·) indicates parameter Nset (t+1) The functional relationship with the water pump is obtained from the water pump model.

[0108] In this embodiment, the constraints in step S4 include a host setting temperature constraint, a water pump setting frequency constraint, and an indoor thermal comfort constraint; the indoor thermal comfort constraint is the maximum heat exchange capacity of the terminal.

[0109] In this embodiment, the host setting temperature constraint is specifically:

[0110]

[0111] Among them, Tset (t+1) Set the host temperature at time t+1.

[0112] In this embodiment, the water pump setting frequency constraint is specifically:

[0113] 30Hz≤Nset (t+1) ≤50Hz

[0114] Among them, Nset (t+1) Set the frequency of the pump at time t+1.

[0115] In this embodiment, the cold and hot water supply temperatures and the water pump frequency affect the heat exchange capacity of the fan coil unit, and thus affect the final state of the processed air. Increasing the chilled water set temperature or reducing the water pump frequency during summer cooling causes the enthalpy value of the supply air state point in the fan coil unit to increase. At this time, the enthalpy difference between the supply and return air states decreases, resulting in a decrease in the heat exchange capacity of the fan coil unit, which in turn causes the room thermal comfort to fail to meet the requirements. Lowering the hot water set temperature or reducing the water pump frequency during winter heating causes the supply air state point temperature in the fan coil unit to decrease. At this time, the temperature difference between the supply and return air states decreases, resulting in a decrease in the heat exchange capacity of the fan coil unit, which in turn causes the room thermal comfort to fail to meet the requirements. Therefore, when the heat exchange capacity of the fan coil unit under different water supply temperatures and water pump frequencies is not lower than the indoor load demand, it can be determined that the indoor thermal comfort meets the requirements. In this embodiment, the maximum heat exchange capacity of the terminal is used as the indoor constraint condition. The calculation formula for the maximum heat exchange capacity of the terminal is:

[0116]

[0117] Among them, y totalc is the sum of the summer heat transfer capacity of all fan coil units, that is, the maximum heat transfer capacity at the end of summer, y totalh is the sum of the winter heat transfer capacity of all fan coil units, that is, the maximum heat transfer capacity at the end of winter, kW; p is the number of fan coil units of different models, y ic is the summer heat exchange capacity of a single fan coil unit, y ih is the winter heat exchange capacity of a single fan coil unit, k ic is the slope of the summer heat transfer capacity equation, k ih is the slope of the winter heat transfer capacity equation, u is the water supply temperature, ℃, b ic is the intercept in summer heat transfer capacity, b ih is the intercept in winter heat transfer capacity, k totalc is the slope of the maximum heat transfer capacity equation at the end of summer, k totalh is the slope of the maximum heat transfer capacity equation at the end of winter, b totalc is the intercept of the maximum heat transfer capacity at the end of summer, b totalh is the intercept of the maximum heat exchange capacity at the terminal in winter, i∈[1,7] and is a positive integer. The number of the seven types of fan coil units are a, b, c, d, e, f, and g respectively, and p is the number of fan coil units of different models.

[0118] In this embodiment, step S5 specifically includes the following steps:

[0119] S51. Set the optimization step and optimization interval of the host set temperature and the water pump set frequency respectively. Since frequent adjustment of the host water outlet temperature and the water pump frequency will affect the operating life of the equipment, the optimization intervals of the host set temperature in summer and winter are set to 7-15°C and 36-45°C respectively in this embodiment, the optimization step is set to 1°C, the optimization interval of the water pump frequency is 30-50Hz, and the optimization interval is 5Hz;

[0120] S52 sets the parameter grid, and traverses all grid nodes according to the optimization step size and optimization interval, and calculates 35 groups of nodes to be optimized in summer and 50 groups of nodes to be optimized in winter according to the optimization interval set in step S51;

[0121] S53. Count all nodes whose heat exchange capacity meets the load demand, and substitute all nodes into the objective function to calculate, and obtain the node corresponding to the minimum objective function, which is the host set temperature Tset at the next moment. t+1 And the pump setting frequency Nset at the next moment t+1 The optimal combination of

[0122] Embodiment 2:

[0123] On the basis of Example 1, data under four different operating conditions in summer and winter were selected for analysis before and after optimization to compare the system operating performance before and after optimization, wherein each operating condition had five sets of operating data.

[0124] In this embodiment, the comparison results of summer operation data are shown in Table 1. The fifth group of data is selected from the four groups of working conditions for energy consumption analysis. Figure 2 , Figure 3 , Figure 4 and Figure 5 As shown in the figure, in summer, 10℃ water temperature and 50Hz water supply temperature can meet the indoor comfort requirements, so the analysis is mainly based on this setting parameter range.

[0125] Table 1 Comparison results before and after optimization of summer working conditions

[0126]

[0127]

[0128] like Figure 2 As shown in Figure 1, in working condition 1, due to the low outdoor temperature and low indoor load demand, the chilled water supply temperature can be increased to 15°C to meet the indoor comfort requirements. At this time, the optimal chilled water supply temperature is calculated to be 15°C, and the water pump setting frequency is 30Hz. At this time, the total energy consumption of the central air-conditioning system reaches the lowest, which is 51.4kW. In addition, according to Figure 2It can be seen that under this operating condition, when the chilled water supply temperature is increased, the total energy consumption of the central air-conditioning system does not decrease significantly, but reducing the water pump frequency can achieve greater energy savings. After optimization, the central air-conditioning water system in this group of operating conditions can achieve an energy saving rate of 33.3%.

[0129] like Figure 3 As shown in the figure, for working condition 2, as the outdoor temperature increases, the indoor load demand increases. At this time, when the chilled water supply temperature is set at 14℃, 15℃, and the pump frequency is 13℃, 30Hz, 35Hz, and 40Hz, the heat exchange capacity of the terminal cannot meet the thermal comfort requirements. Increasing the pump frequency can effectively reduce the host operation energy consumption, and the host energy consumption reduction value is higher than the pump energy consumption increase value, thereby improving the overall operation energy efficiency of the central air-conditioning system. However, when the pump frequency is increased to 40Hz, the increase in pump energy consumption is too large, which offsets the host energy consumption reduction value. Therefore, when the pump frequency is set to 40Hz and above, the overall energy consumption of the central air-conditioning system is too large. At this time, according to the optimization algorithm, the optimal chilled water setting temperature under this condition is calculated to be 12℃, the pump frequency is 35Hz, and the total operating energy consumption is 118.4kW. After optimization, 16.8% of energy saving can be achieved in this group of working conditions.

[0130] like Figure 4 As shown, the load demand in condition 3 is higher. At this time, the setting parameters that meet the indoor comfort requirements are only 11°C and 40Hz, 45Hz, 50Hz and 10°C. The operating performance is similar to that of condition 2. When the water pump frequency increases to 40Hz and above, the total energy consumption of the central air-conditioning system increases. At this time, the optimal chilled water setting temperature is calculated to be 10°C, the water pump setting frequency is 35Hz, and the total operating energy consumption is 159.3kW. After optimization, 11.9% energy saving can be achieved in this group of conditions.

[0131] like Figure 5 As shown, in working condition 4, the outdoor temperature is the highest and the load demand is also the largest. At this time, only 40Hz, 45Hz and 50Hz at a chilled water setting temperature of 10℃ meet the indoor thermal comfort requirements. The minimum energy consumption is calculated to be 221.8kW, the optimal chilled water setting temperature is 10℃, and the water pump setting frequency is 40Hz. After optimization, 6.4% energy saving can be achieved in this group of working conditions.

[0132] In this embodiment, the comparison results of winter operation data are shown in Table 3. The fifth group of data is also selected for energy consumption analysis in the four groups of working conditions. Figure 6 , Figure 7 , Figure 8 and Fig. 9 shown.

[0133] Table 2 Comparison results before and after optimization of summer working conditions

[0134]

[0135]

[0136] like Figure 6 As shown in Figure 1, in working condition 1, due to the high outdoor temperature and low indoor load demand, the hot water temperature setting value of 36°C and the water pump frequency setting of 30Hz can meet the indoor comfort requirements. It is calculated that the energy consumption of the central air-conditioning system reaches the lowest under the set parameters, which is 52.5kW. Similarly, when the hot water supply temperature is reduced under this working condition, the total energy consumption of the central air-conditioning system does not show a significant downward trend, while reducing the water pump frequency can achieve greater energy savings. After optimization, the central air-conditioning water system in this group of working conditions can achieve an energy saving rate of 36.1%.

[0137] like Figure 7 As shown in the figure, for working condition 2, as the outdoor temperature decreases, the indoor load demand increases. At this time, the 30Hz, 35Hz and 40Hz pump frequencies at 36°C cannot meet the indoor comfort requirements. The optimal hot water setting temperature is calculated to be 37°C. At the same time, because the load is still low, the overall operating energy consumption of the central air-conditioning system will increase after increasing the water pump frequency. Therefore, the optimal water pump frequency is calculated to be 30Hz. After optimization, 25.9% energy saving can be achieved in this group of working conditions.

[0138] like Figure 8 As shown, the load demand in condition 3 is higher. At this time, the hot water setting temperature of 37°C and the pump frequency of 45Hz, 50Hz and the hot water setting temperature of 38°C-45°C can meet the indoor demand. The operating performance is similar to that of conditions 2 and 3 in the summer cooling mode. When the water pump frequency increases to 40Hz and above, the total energy consumption of the central air-conditioning system increases. At this time, the optimal hot water setting temperature is calculated to be 38°C, the water pump setting frequency is 35Hz, and the total operating energy consumption is 113.2kW. After optimization, an energy saving rate of about 18.5% can be achieved.

[0139] like Fig. 9 As shown, the load demand in working condition 4 is the largest, at about 460kW. At this time, the indoor comfort requirements can be met under the parameters of hot water setting temperature of 41℃-45℃ and 40℃ and pump frequency of 50Hz. The minimum energy consumption is calculated to be 145kW, the optimal hot water setting temperature is 41℃, and the water pump setting frequency is 35Hz, which can achieve energy savings of about 14.1%.

[0140] Embodiment 3:

[0141] On the basis of Example 1, MATLAB is used to compile an optimized operation method of the air source heat pump-fan coil central air conditioning system provided in Example 1 and is imported into the TRNSYS module for simulation analysis.

[0142] The actual start-up time of the central air-conditioning system equipment is around 8 o'clock on weekdays, but the optimization algorithm optimizes the best operating parameters at 9 o'clock based on the operating data at 8 o'clock in the morning, and calculates hourly in this order. Therefore, it is impossible to directly optimize the operating data at 8 o'clock, and it is necessary to set the initial operating state at this time.

[0143] In this embodiment, the load data at 8 o'clock in the morning in summer and winter are statistically analyzed, and it is found that the maximum cooling load at this moment under summer conditions is about 500kW, and the maximum heating load at this moment under winter conditions is about 400kW. Combined with the changes in the terminal refrigeration and heating capacities under the above-mentioned different host setting water temperature and water pump frequency combinations, it is found that a water supply temperature of 12°C and a water pump frequency of 50Hz in summer and a water supply temperature of 38°C and a water pump frequency of 50Hz in winter can meet the requirements. Therefore, the initial setting parameters at 8 o'clock on working days are determined as a chilled water setting temperature of 12°C and a water pump setting frequency of 50Hz in summer, and a hot water setting temperature of 38°C and a water pump frequency of 50Hz in winter.

[0144] The optimization results and operation energy consumption comparison results in summer and winter are as follows: Fig.10 , Fig.11 , Fig.12 and Fig.13 As shown in Table 3, the operating energy consumption of the central air-conditioning system in summer and winter, the main engine operating COP, and the water system operating COP before and after optimization are shown in Table 3. It can be found that the total energy consumption of the main engine operation under the summer cooling condition is reduced from 69476kWh to 65845.67kWh after optimization, which is only about 5.23% lower, while the water pump energy consumption is reduced from 18244.61kWh to 5868.04kWh, with an energy saving rate of up to 67.84%, and the main engine operation COP is increased from 3.15 to 3. .29, and the water system operation COP increased from 2.40 to 2.99; under winter heating conditions, the main engine operation energy consumption decreased from 34934.94kWh to 29059.28kWh, a decrease of 17.82%, while the water pump energy consumption decreased from 11009.68kWh to 3444.32kWh, and the energy saving rate was still above 65%. At this time, the main engine operation COP increased from 2.91 to 3.47, and the water system operation COP increased from 2.15 to 3.09. Analysis of the annual operation data shows that the main engine annual energy saving is 9506.83kWh, and the energy saving rate is about 9%; the water pump annual energy saving is 19941.93kWh, and the energy saving rate is about 68%; the system annual energy saving is 29448.76kWh, and the energy saving rate is about 22%. The above data show that the energy saving rate achieved by adjusting the pump frequency is much higher than that achieved by adjusting the hot and cold water supply temperature; in addition, the energy saving rate of the main unit is lower under summer cooling conditions. This is because the summer conditions before optimization were simulated and calculated according to the 10°C chilled water set temperature, which has achieved some energy saving compared to the 7°C water supply temperature required by the specification. Overall, the energy saving effect of the central air-conditioning system in summer and winter is significant.

[0145] Table 3 Comparison of annual air conditioning system energy consumption results

[0146]

[0147]

[0148] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. An optimized operation method of an air source heat pump-fan coil central air conditioning system, characterized in that: The method comprises the following steps: S1. Obtain the influencing factors of building load and outdoor meteorological parameters; S2. Construct a central air conditioning load prediction model and an outdoor meteorological parameter prediction model based on the influencing factors, and predict the load demand Q at the next moment. t+1 , the outdoor ambient temperature Tdb at the next moment t+1 and the outdoor relative humidity RH at the next moment t+1 ; S3. Determine the main influencing factors of the operating performance of the air source heat pump and the water pump, build a data-driven model of the air source heat pump and the water pump, and perform simulation operation based on the data-driven model to obtain the total energy consumption of the central air-conditioning system; S4. Based on the total energy consumption of the central air-conditioning system and the load demand Q at the next moment t+1 , the outdoor ambient temperature Tdb at the next moment t+1 and the outdoor relative humidity RH at the next moment t+1 Based on the prediction results, set the optimization objective function and constraints; S5. Use the grid search optimization algorithm to solve the optimization objective function and constraints to obtain the host set temperature Tset at the next moment t+1 And the pump setting frequency Nset at the next moment t+1 , completing the optimization process.

2. The method for optimizing the operation of the air source heat pump-fan coil central air conditioning system according to claim 1, characterized in that: The step S2 specifically includes the following steps: S21. Perform normalization processing on the influencing factors, and the formula for the normalization processing is: Among them, v' is the value after normalization, v is the value before normalization, and v max is the maximum value of the parameter before normalization, v min is the minimum value of the parameter before normalization; S22. Calculate the correlation coefficient between the normalized influencing factors and the cooling and heating loads. The calculation formula of the correlation coefficient is: Among them, r p is the correlation coefficient, q is the number of influencing factors, X s is the sth influencing factor, is the average value of the influencing factors, Y s is the sth building load, is the average value of the building load; S23. Determine the input parameters and output parameters of the XGBoost model according to the correlation coefficient, set the hyperparameters of the XGBoost model, and train the XGBoost model; S24. Optimize the trained XGBoost model using the sparrow search algorithm to obtain a central air conditioning load prediction model and an outdoor meteorological parameter prediction model; S25. Input the current time t, date, outdoor dry-bulb temperature at time t, outdoor wet-bulb temperature at time t and building load at time t into the central air-conditioning load prediction model to obtain the output data of the central air-conditioning load prediction model; S26. Input the outdoor dry-bulb temperature at the current time t, the outdoor dry-bulb temperature at the time t, and the outdoor wet-bulb temperature at the time t into the outdoor meteorological parameter prediction model to obtain the output data of the outdoor meteorological parameter prediction model; S27. Denormalize the output data of the central air conditioning load prediction model to obtain the load demand Q at the next moment. t+1 , and the output data of the outdoor meteorological parameter prediction model is denormalized to obtain the outdoor ambient temperature Tdb at the next moment t+1 and the outdoor relative humidity RH at the next moment t+1 ; The formula for the denormalization process is: y=y'·(y max -and min )+y min Among them, y is the value of the output data after denormalization, y' is the value of the output data before denormalization, and y max is the maximum value before load normalization in the training data, y min is the minimum value of the load in the training data before normalization.

3. The method for optimizing the operation of the air source heat pump-fan coil central air conditioning system according to claim 2, characterized in that: The objective function of the XGBoost model during training is: Among them, Obj is the objective function of the XGBoost model, I j is the set of all samples belonging to leaf node j, g l is the first-order partial derivative of the lth sample in leaf node j, h l is the second-order partial derivative of the lth sample in leaf node j, λ is the regularization parameter, n is the total number of training data samples, γT is the regularization coefficient, γ is the adjustment coefficient, and T is the number of leaf nodes in the tree.

4. The method for optimizing the operation of an air source heat pump-fan coil central air conditioning system according to claim 1, characterized in that: The data-driven models of the air source heat pump and the water pump in step S3 include an air source hot water pump model and a water pump model.

5. The method for optimizing the operation of the air source heat pump-fan coil central air conditioning system according to claim 4, characterized in that: The objective function in step S4 is the total energy consumption of the system operation at the next moment, and the specific expression formula is: P total(t+1) =P ashp(t+1) +P pump(t+1) <h2 style=";text-align:left;direction:ltr">=f1(Tdb<h2 style=";text-align:left;direction:ltr"> (t+1) <h2 style=";text-align:left;direction:ltr"> RH<h2 style=";text-align:left;direction:ltr"> (t+1) <h2 style=";text-align:left;direction:ltr"> Tset<h2 style=";text-align:left;direction:ltr"> (t+1) <h2 style=";text-align:left;direction:ltr"> Nset<h2 style=";text-align:left;direction:ltr"> (t+1) <h2 style=";text-align:left;direction:ltr"> ,Q<h2 style=";text-align:left;direction:ltr"> (t+1) <h2 style=";text-align:left;direction:ltr"> )+f3(Nset<h2 style=";text-align:left;direction:ltr"> (t+1) <h2 style=";text-align:left;direction:ltr"> ) Among them, P total(t+1) is the total energy consumption of the central air-conditioning system at time t+1, P ashp(t+1) is the operating energy consumption of the heat pump at time t+1, P pump(t+1) is the operating energy consumption of the pump at time t+1, Tdb (t+1) is the outdoor dry-bulb temperature at time t+1, RH (t+1) is the outdoor relative humidity at time t+1, Tset (t+1) Set the host temperature at time t+1, Nset (t+1) is the pump set frequency at time t+1, Q (t+1) is the load demand at time t+1, f1(·) represents the parameter Tdb (t+1) RH (t+1) 、Tset (t+1) 、Nset (t+1) and Q (t+1) The functional relationship with the host is obtained from the air source hot water pump model, and f3(·) represents the parameter Nset (t+1) The functional relationship with the water pump is obtained from the water pump model.

6. The method for optimizing the operation of an air source heat pump-fan coil central air conditioning system according to claim 1, characterized in that: The constraints in step S4 include host setting temperature constraints, water pump setting frequency constraints and indoor thermal comfort constraints; the indoor thermal comfort constraints are the maximum heat exchange capacity of the terminal.

7. The method for optimizing the operation of the air source heat pump-fan coil central air conditioning system according to claim 6, characterized in that: The host setting temperature constraint is specifically: Among them, Tset (t+1) Set the host temperature at time t+1.

8. The method for optimizing the operation of an air source heat pump-fan coil central air conditioning system according to claim 6, characterized in that: The pump setting frequency constraint is specifically: 30Hz≤Nset (t+1) ≤50Hz Among them, Nset (t+1) Set the frequency of the pump at time t+1.

9. The method for optimizing the operation of an air source heat pump-fan coil central air conditioning system according to claim 6, characterized in that: The calculation formula of the maximum heat exchange capacity of the terminal is: Among them, y totalc is the sum of the summer heat transfer capacity of all fan coil units, that is, the maximum heat transfer capacity at the end of summer, y totalh is the sum of the heat transfer capacity of all fan coil units in winter, that is, the maximum heat transfer capacity at the end of winter, p is the number of fan coil units of different models, y ic is the summer heat exchange capacity of a single fan coil unit, y ih is the winter heat exchange capacity of a single fan coil unit, k ic is the slope of the summer heat transfer capacity equation, k ih is the slope of the winter heat transfer capacity equation, u is the water supply temperature, b ic is the intercept in summer heat transfer capacity, b ih is the intercept in winter heat transfer capacity, k totalc is the slope of the maximum heat transfer capacity equation at the end of summer, k totalh is the slope of the maximum heat transfer capacity equation at the end of winter, b totalc is the intercept of the maximum heat transfer capacity at the end of summer, b totalh is the intercept of the maximum heat exchange capacity at the terminal in winter, i is the total number of fan coil types, i∈[1,7], g and a represent the maximum and minimum number of different models, respectively.

10. The method for optimizing the operation of an air source heat pump-fan coil central air conditioning system according to claim 1, characterized in that: The step S5 specifically comprises the following steps: S51. Set the optimization step and optimization interval of the host set temperature and the water pump set frequency respectively; S52. Set the parameter grid and traverse all grid nodes according to the optimization step size and optimization interval; S53. Count all nodes whose heat exchange capacity meets the load demand, and substitute all nodes into the objective function to calculate, and obtain the node corresponding to the minimum objective function, which is the host set temperature Tset at the next moment. t+1 And the pump setting frequency Nset at the next moment t+1 The optimal combination of

Images