An energy-saving method for a central air conditioning system based on intelligent control

Abstract

The application provides an energy-saving method for a central air conditioning system based on intelligent control, which comprises the following steps: firstly, counting and preprocessing the operation data of the central air conditioning system under different working conditions; secondly, based on the mechanism framework of the equipment, a mathematical model capable of fully reflecting the performance of each equipment of the system is established by using the preprocessed data; then, the constraint and coupling relationship among the equipment in the central air conditioning system are built; finally, based on the end cold load demand, the global optimization calculation of the central air conditioning system is carried out by using a genetic algorithm, so that the most energy-saving operation working condition under the end cold load demand is obtained, and a control instruction is issued to realize the energy-saving operation of the central air conditioning system. The application can be used for the energy-saving optimization operation control of the central air conditioning system, and based on the genetic algorithm, the most energy-saving operation mode is quickly solved from tens of thousands of operation combinations, the energy-saving performance of the real-time control of the central air conditioning system is realized, and the problem of excessive energy consumption of the central air conditioning system is solved.

Description

Technical Field

[0001] This invention belongs to the field of energy-saving optimization and control technology for centralized air conditioning systems, specifically relating to an energy-saving method for central air conditioning systems based on intelligent control. Background Technology

[0002] Currently, central air conditioning systems typically account for over 45% of a building's total energy consumption, representing a significant energy drain. Accurately understanding the performance characteristics of each component within the central air conditioning system and establishing suitable models are prerequisites for developing reasonable energy-saving optimization and control schemes. Current industry optimization of central air conditioning systems largely focuses on individual components or optimizes the entire system around a chiller unit, lacking a globally optimized intelligent control system. However, a central air conditioning system is a unified whole, with strong coupling between its components. Optimizing only a single component cannot achieve deep optimization and may even lead to higher overall system energy consumption. Furthermore, the industry employs two main techniques for establishing equipment performance models: purely physical models and purely data-driven models. Purely physical models can achieve relatively accurate results with limited data, but they require numerous internal parameters that are difficult to obtain and thus hard to apply in practical engineering. Purely data-driven models, such as neural network models, require extensive operational data for modeling, and their quality depends heavily on the quality of the training data, making them difficult to apply in the early stages of a project or when operational data is scarce. Summary of the Invention

[0003] The technical problem to be solved by this invention is to provide an energy-saving method for a central air conditioning system based on intelligent control. This method solves the problem that, in actual operation, the central air conditioning system is difficult to achieve its most energy-efficient operating state when real-time adjustment and control is performed according to changes in terminal cooling load due to the large number of devices and the complex coupling relationship. This method realizes intelligent control of the central air conditioning system and greatly reduces the operating energy consumption of the central air conditioning system.

[0004] The objective of this invention is achieved through the following solution: an energy-saving method for a central air conditioning system based on intelligent control, comprising the following steps:

[0005] Step 1: Perform statistical analysis and data preprocessing of the actual operating data of the central air conditioning system;

[0006] Step 2: Establish a COP performance model for the chiller unit based on data-driven and mechanistic frameworks;

[0007] Step 3: Establish an energy consumption model for the water pump based on data-driven approaches and a mechanistic framework;

[0008] Step 4: Establish an energy consumption model for the cooling tower based on data-driven and mechanistic frameworks;

[0009] Step 5: Use a genetic algorithm to optimize the main control variables of the total energy consumption of the central air conditioning system.

[0010] Furthermore, the specific steps for statistical analysis and preprocessing of the actual operating data of the central air conditioning system in step one include:

[0011] ① Data statistics: First, it is necessary to collect the actual operating data of the central air conditioning system under various operating conditions, including: (a) chilled water supply temperature; (b) chilled water return temperature; (c) chiller unit operating power; (d) chilled water flow rate; (e) cooling water outlet temperature; (f) cooling water inlet temperature; (g) cooling water flow rate; (h) operating frequency of chilled water pump and cooling water pump; (i) power of chilled water pump and cooling water pump; (j) the control pressure difference value set by the system.

[0012] ② Data Screening: After completing the actual data statistics, data screening is carried out. The cooling load of the central air conditioning system is calculated using equation (1), the total heat output of the system is calculated using equation (2), the load imbalance rate is calculated using equation (3), and the chiller COP is calculated using equation (4). All abnormal data with an imbalance rate exceeding 15%, COP values ​​outside the range of (μ-3σ, μ+3σ), and chilled water pump operating frequencies below 30Hz and above 50Hz are removed. The rules for identifying abnormal COP values ​​are as follows: where μ is the average COP of all data, and σ is the standard deviation of COP of all data. After completing the data statistics and preprocessing, the equipment energy consumption model can be established.

[0013] Q e =c·m chw ·(T chwr -T chws Equation (1)

[0014] Q c =c·m cw ·(T cwo -T cwi Equation (2)

[0015]

[0016] In the formula, Q e The cooling load of the central air conditioning system is kW; c is the specific heat capacity of water, kJ / kg·℃; m chw The volumetric flow rate of chilled water is m. 3 / s;T chwr T represents the chilled water return temperature, in °C. chws Q represents the chilled water supply temperature, in °C. cCooling capacity of the chiller, kW; m cw The volumetric flow rate of the cooling water is m. 3 / s;T cwo T represents the outlet temperature of the cooling water, in °C. cwi B represents the cooling water inlet temperature, in °C. a P1 is the load imbalance rate; P1 is the energy consumption of the refrigeration unit (kW); COP is the energy efficiency ratio of the refrigeration unit.

[0017] Furthermore, the specific steps of step two, which establishes the COP performance model of the chiller unit based on data-driven and mechanistic frameworks, include: after filtering the data in step one, based on the measured cooling load Q of the central air conditioning system... e Chilled water supply temperature T chws Cooling water inlet temperature T cwi The mechanism framework of the chiller unit shown in equation (5) is established, and all parameters from a1 to a8 are identified by the least squares method, thereby establishing the COP performance model of the chiller unit. Then, the energy consumption P of the chiller unit is calculated using equation (6).

[0018] COP = a1 + a2·Q e +a3·T chws +a4·T cwi +a5·Q e 2 +a6·Q e ·T chws +a7·Q e ·T cwi +a8·T chws ·T cwi Equation (5)

[0019]

[0020] In the formula, P1 is the energy consumption of the refrigeration unit, in kW; T chws T represents the chilled water supply temperature, in °C. cwi Q represents the cooling water inlet temperature, in °C. e The cooling load of the central air conditioning system is expressed in kW; a i These are model parameters, which can be identified and obtained based on the actual operating data of the chiller unit, i = 1, 2, 3...

[0021] Furthermore, the specific steps of step three, which establishes the energy consumption model of the water pump based on data-driven and mechanistic framework, include: establishing the mechanistic framework of the chilled water pump and cooling water pump as shown in equations (7) and (8). The energy consumption of the chilled water pump and cooling water pump can be calculated through equation (7), where n in equation (7) is calculated by equation (8), and β in equation (8) is determined by the position of the differential pressure control point. The closer to the end, the smaller the β value, and the closer to the water pump, the larger the β value. Its value range is 0 to 1. After calculating n, the parameters of equation (7) are identified based on the filtered data to obtain b1 and b2.

[0022] P 2，3 =b1·m n + b2 Equation (7) n = -1.3429·β + 2.35 Equation (8)

[0023] In the formula, P 2，3 The energy consumption of the chilled and cooling water pump is expressed in kW; m is the current volumetric flow rate of the pump, expressed in m³ / s. 3 / s; β is the differential pressure control ratio, which is the ratio of the system control differential pressure to the system rated differential pressure. The value of β varies depending on the control point; n is the flow rate exponent under different differential pressure control ratios β; b i The coefficients are the model fitting coefficients, i = 1, 2.

[0024] Furthermore, the specific steps of step four, which establishes the energy consumption model of the cooling tower based on data-driven and mechanistic framework, include: establishing the energy consumption model of the cooling tower based on data-driven and mechanistic framework to calculate the system energy consumption. Based on the mechanistic framework of cooling tower air volume and energy consumption, the actual air volume model of the cooling tower fan is first established using equations (9) to (13), where d1 to d9 can be identified and obtained using the least squares method based on actual operating data. Finally, based on the operating data of the actual air volume and actual power of the cooling tower fan using formula (13), the characteristic parameters c0 to c3 are identified and obtained using the least squares method, thereby establishing the energy consumption model of the cooling tower.

[0025]

[0026] T app =T cwi -T wb Equation (1O)

[0027] △T cw =T cwo -T cwi Equation (11)

[0028]

[0029] In the formula, T appThe approximation degree of the cooling tower is expressed in °C; T. wb Outdoor wet-bulb temperature, °C; ΔT cw The temperature difference between the inlet and outlet of the cooling water, in °C; T cwo f is the cooling water outlet temperature, in °C; f is the actual operating frequency of the cooling tower fan, in Hz; f0 is the rated operating frequency of the cooling tower fan, in Hz; m cw The cooling water flow rate is m 3 / h;d i P represents the model fitting coefficients, i = 1, 2, 3…; P4 represents the actual power consumption of the cooling tower fan, in kW; P tfan，0 The theoretical power consumption of the cooling tower fan under rated conditions is kW; m a The actual air volume of the cooling tower fan is in meters. 3 / h;m a,0 The rated air volume of the cooling tower fan is in meters. 3 / h; ci are the model fitting coefficients, i = 1, 2, 3...

[0030] Furthermore, the specific steps of step five, which uses a genetic algorithm to optimize the main control variables of the total energy consumption of the central air conditioning system, include: using a genetic algorithm to optimize the main control variables of the total energy consumption of the central air conditioning system. As shown in equation (14), based on the energy consumption model of each device in the central air conditioning system established above, the total energy consumption of the entire central air conditioning system is obtained. See equation (15), establish the constraints and coupling relationships between the devices in the central air conditioning system, with the total energy consumption P of the system as the basis. total With the goal of minimizing the overall energy consumption of the central air conditioning system, and using the chilled water supply temperature, cooling water return temperature, cooling water supply and return temperature difference, chilled water supply and return temperature difference, and the number of operating chillers, chilled water pumps, cooling water pumps, and cooling towers as optimization variables, a genetic algorithm is used in conjunction with the constraints between the equipment to perform optimization calculations. This yields the control parameters that minimize the total energy consumption of the central air conditioning system, including the chilled water supply temperature, cooling water return temperature, cooling water supply and return temperature difference, chilled water supply and return temperature difference, and the number of operating chillers, chilled water pumps, cooling water pumps, and cooling towers. This achieves overall optimized control of the central air conditioning system.

[0031] P total =P1+P2+P3+P4 Equation (14)

[0032]

[0033] In the formula: P total Total energy consumption of the central air conditioning system, kW; P1 is the energy consumption of the chiller unit, kW; P 2，3 P1 represents the energy consumption of the chilled water pumps, in kW; P4 represents the energy consumption of the cooling tower, in kW.

[0034] Compared with existing technologies, the beneficial effects of the technical solution of this invention are as follows: This invention adopts a central air conditioning system energy consumption model establishment technology based on data-driven and mechanism framework. It can obtain a central air conditioning system performance model with strong adaptability applicable to actual projects by using actual data-driven modeling based on the physical model framework of energy-consuming equipment. It can well reflect the actual operating energy consumption under different operating conditions, greatly improve the prediction accuracy of the models of various equipment in the chiller plant, and quickly solve the most energy-saving operating mode from tens of thousands of operating combinations based on genetic algorithm. It realizes the energy-saving performance of the real-time control scheme of the central control system, solves the problem of excessive energy consumption of the central control system, and has important significance for the realization of my country's "3060" target. Attached Figure Description

[0035] Figure 1 This is a flowchart illustrating the energy-saving optimization process of the central air conditioning system involved in this invention.

[0036] Figure 2 This is a comparison chart of the measured COP and predicted COP of chiller unit #1 in this invention;

[0037] Figure 3 This is a comparison chart of the measured COP and predicted COP of chiller unit #2 in this invention;

[0038] Figure 4 This is a comparison chart of the predicted energy consumption and the measured energy consumption of the chilled water pump energy consumption model in this invention;

[0039] Figure 5 This is a comparison chart of the predicted energy consumption and the measured energy consumption of the cooling water pump energy consumption model in this invention;

[0040] Figure 6 This is a comparison chart of the predicted energy consumption and the measured energy consumption of the cooling tower energy consumption model in this invention;

[0041] Figure 7 These are the solution steps for the total energy consumption optimization model of the central air conditioning system involved in this invention;

[0042] Figure 8 This is a dynamic optimization diagram of the optimal combination of control parameters in the central air conditioning control of this invention. Detailed Implementation

[0043] The present invention will now be described in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustrative and explanatory purposes only and are not intended to limit the scope of the invention. After reading the teachings of this invention, those skilled in the art can make various alterations or modifications to the invention, and these equivalent forms also fall within the scope defined by the appended claims.

[0044] This embodiment focuses on a subway station in Chengdu. Its central air conditioning system's chiller room contains two screw chillers, two chilled water pumps, and a cooling water pump. Two cooling towers are located above the station. The parameters of each device in the system are shown in Table 1 below.

[0045] Table 1 Parameters of Various Equipment in the Cooling Plant

[0046]

[0047] An energy-saving method for a central air conditioning system based on intelligent control is described in the appendix. Figure 1 The specific implementation includes the following steps:

[0048] Step 1: Perform statistical analysis and data preprocessing of the actual operating data of the central air conditioning system. The raw data contains a large number of missing and outlier values; removing low-quality data can improve the reliability of the model. This step can be divided into two sub-steps:

[0049] ① Data statistics: First, it is necessary to collect the actual operating data of the central air conditioning system under various operating conditions, including: (a) chilled water supply temperature; (b) chilled water return temperature; (c) chiller unit operating power; (d) chilled water flow rate; (e) cooling water outlet temperature; (f) cooling water inlet temperature; (g) cooling water flow rate; (h) operating frequency of chilled water pump and cooling water pump; (i) power of chilled water pump and cooling water pump; (j) the control pressure difference value set by the system.

[0050] ② Data Screening: After completing the actual data statistics, data screening is carried out. The cooling load of the central air conditioning system is calculated using equation (1), the total heat output of the system is calculated using equation (2), the load imbalance rate is calculated using equation (3), and the chiller COP is calculated using equation (4). All abnormal data with an imbalance rate exceeding 15%, COP values ​​outside the range of (μ-3σ, μ+3σ), and chilled water pump operating frequencies below 30Hz and above 50Hz are removed. The rules for identifying abnormal COP values ​​are as follows: where μ is the average COP of all data, and σ is the standard deviation of COP of all data. After completing the data statistics and preprocessing, the equipment energy consumption model can be established.

[0051] Q e =c·m chw ·(T chwr -T chws Equation (1)

[0052] Q c =c·m cw ·(T cwo -T c wi) Equation (2)

[0053]

[0054] In the formula, Q e The cooling load of the central air conditioning system is kW; c is the specific heat capacity of water, kJ / kg·℃; m chw The volumetric flow rate of chilled water is m. 3 / s;T chwr T represents the chilled water return temperature, in °C. chws Q represents the chilled water supply temperature, in °C. c Cooling capacity of the chiller, kW; m cw , where m is the volumetric flow rate of the cooling water. 3 / s;T cwo T represents the outlet temperature of the cooling water, in °C. cwi B represents the cooling water inlet temperature, in °C. a P1 is the load imbalance rate; P1 is the energy consumption of the refrigeration unit (kW); COP is the energy efficiency ratio of the refrigeration unit.

[0055] Step Two: Establish the COP performance model of the chiller unit based on data-driven and mechanistic frameworks. After data screening in Step One, the COP performance model is established based on the measured cooling load Q of the central air conditioning system. e Chilled water supply temperature T chws Cooling water inlet temperature T cwi Establish the mechanism framework of the chiller unit as shown in equation (5), use the least squares method to identify all parameters a1 to a8, and thus establish the COP performance model of the chiller unit. Then use equation (6) to calculate the energy consumption P1 of the chiller unit.

[0056] COP = a1 + a2·Q e +a3·T chws +a4·T cwi +a5·Q e 2 +a6·Q e ·T chws +a7·Q e ·T cwi +a8·T chws ·T cwi Equation (5)

[0057]

[0058] In the formula, P1 is the energy consumption of the refrigeration unit, in kW; T chws T represents the chilled water supply temperature, in °C. cwi Q represents the cooling water inlet temperature, in °C. e The cooling load of the central air conditioning system is expressed in kW; a i These are model parameters, which can be identified and obtained based on the actual operating data of the chiller unit, i = 1, 2, 3...

[0059] The calculated COP performance model fitting coefficients for the two screw chiller units in this embodiment are shown in Tables 2 and 3 below. A comparison chart of predicted and measured COP values ​​is attached. Figure 2 and attached Figure 3 The simulation fitting coefficients of determination R² were 0.957 and 0.932, respectively, indicating that the COP performance model had good prediction accuracy.

[0060] Table 2 Calculation results of fitting coefficients for model of chiller unit #1

[0061]

[0062] Table 32# Chiller Unit Model Fitting Coefficient Calculation Results

[0063]

[0064] Step 3: Establish the energy consumption model of the water pump based on data-driven and mechanistic framework. Establish the mechanistic framework of the chilled water pump and cooling water pump as shown in equations (7) and (8). The energy consumption of the chilled water pump and cooling water pump can be calculated through equation (7). In equation (7), n is calculated by equation (8). In equation (8), β is determined by the position of the differential pressure control point. The closer to the end, the smaller the value of β. The closer to the water pump, the larger the value of β. Its value range is 0 to 1. After calculating n, the parameters of equation (7) are identified according to the filtered data to obtain b1 and b2.

[0065] P 2，3 =b1·m n +b2 Equation (7)

[0066] n = -1.3429·β + 2.35 Equation (8)

[0067] In the formula, P 2，3 The energy consumption of the chilled and cooling water pump is expressed in kW; m is the current volumetric flow rate of the pump, expressed in m³ / s. 3 / s; β is the differential pressure control ratio, which is the ratio of the system control differential pressure to the system rated differential pressure. The value of β varies depending on the control point; n is the flow rate exponent under different differential pressure control ratios β; b i The coefficients are the model fitting coefficients, i = 1, 2.

[0068] In this embodiment, the most unfavorable terminal pressure difference control method is adopted, with a chilled water side pressure difference control ratio β of 0.484 and a cooling side pressure difference control ratio of 0.261. The calculated fitting coefficients of the water pump in this embodiment are shown in Tables 4 and 5 below. A comparison chart of the predicted and measured water pump energy consumption results is attached. Figure 4 With appendix Figure 5 .

[0069] Table 4. Calculation results of fitting coefficients for the performance model of chilled water pumps

[0070]

[0071] Table 5. Calculation results of fitting coefficients for the performance model of the cooling water pump.

[0072]

[0073] Step 4: Establish a cooling tower energy consumption model based on data-driven and mechanistic framework to calculate system energy consumption. Based on the mechanistic framework of cooling tower airflow and energy consumption, firstly, establish the actual airflow model of the cooling tower fan using equations (9) to (12), where d1 to d9 can be obtained by using the least squares method based on actual operating data. Finally, based on the operating data of actual airflow and actual power of the cooling tower fan using equation (13), the characteristic parameters c0 to c3 are obtained by using the least squares method, thereby establishing the cooling tower energy consumption model.

[0074] The calculated fitting coefficients for the cooling tower in this embodiment are shown in Tables 6 and 7 below. A comparison chart of the predicted and measured energy consumption results for the cooling tower is attached. Figure 6 .

[0075] Table 6. Calculation results of the fitting coefficient for the cooling tower approximation degree

[0076]

[0077]

[0078] Table 7 Calculation results of the fitting coefficient for predicted energy consumption of cooling towers

[0079]

[0080] Step 5: Use a genetic algorithm to optimize the main control variables of the total energy consumption of the central air conditioning system. Based on the energy consumption models of each device in the central air conditioning system established above, the total energy consumption of the entire central air conditioning system is obtained, as shown in Equation (14). The constraints and coupling relationships between the devices in the central air conditioning system are established, as shown in Equation (15). The total energy consumption P of the system is then used as the basis for the optimization. total With the goal of minimizing energy consumption, and using chilled water supply temperature, cooling water return temperature, cooling water supply-return temperature difference, chilled water supply-return temperature difference, and the number of operating chillers, chilled water pumps, cooling water pumps, and cooling towers as optimization variables, a genetic algorithm is employed, combined with constraints between equipment, to perform optimization calculations. This yields control parameters that minimize the total energy consumption of the air conditioning system, including chilled water supply temperature, cooling water return temperature, cooling water supply-return temperature difference, chilled water supply-return temperature difference, and the number of operating chillers, chilled water pumps, cooling water pumps, and cooling towers. This achieves overall optimized control of the central air conditioning system, thereby reducing system energy consumption. The calculation logic flowchart is attached. Figure 7 .

[0081] The genetic algorithm control parameter optimization process at a certain moment in this embodiment is shown in the appendix. Figure 8 To facilitate the measurement of optimization results, this embodiment screens the operating periods throughout the year. This embodiment selects 12 similar days from June to August for comparative verification of energy-saving effects. The selected time periods are 7:00-21:00, with similar outdoor temperatures (average outdoor temperature greater than 26℃) and outdoor weather conditions, but different operating models (normal mode and energy-saving mode). The power consumption of the central air conditioning system is compared and analyzed, and the results are shown in Table 8.

[0082] Table 8. Power Consumption of Air Conditioning System on Similar Days

[0083]

[0084] As can be seen, under similar daily conditions (a total of 12 days), the intelligent control mode of the present invention reduces the total power consumption by 5575.59 kWh compared with the conventional mode, with a power saving rate of 23.6%, demonstrating significant energy-saving effect.

[0085] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the specific embodiments described above. The specific embodiments and descriptions in the specification are merely for further illustrating the principles of the invention. Various changes and modifications can be made to the present invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the claims and their equivalents.

Claims

1. An energy-saving method for a central air conditioning system based on intelligent control, characterized in that: Includes the following steps: Step 1: Perform statistical analysis and data preprocessing of the actual operating data of the central air conditioning system; Step 2: Establish a COP performance model for the chiller unit based on data-driven and mechanistic frameworks; Step 3: Establish an energy consumption model for the water pump based on data-driven and mechanistic frameworks; Step 4: Establish an energy consumption model for the cooling tower based on data-driven and mechanistic frameworks; Step 5: Use a genetic algorithm to optimize the main control variables of the total energy consumption of the central air conditioning system. Step three specifically includes: establishing the mechanism framework of chilled water pump and cooling water pump as shown in equations (7) and (8); the energy consumption of chilled water pump and cooling water pump can be calculated through equation (7), where n in equation (7) is calculated by equation (8), and β in equation (8) is determined by the location of the differential pressure control point, with the value of β ranging from 0 to 1; after calculating n, the parameters of equation (7) are identified based on the filtered data to obtain b1 and b2; finally, the real-time energy consumption of the pump under any operating condition is calculated based on equation (7). P 2，3 =b1·m n +b2 Equation (7) n = -1.3429·β + 2.35 Equation (8) In the formula, P 2，3 The energy consumption of the chilled water pump and cooling water pump is expressed in kW; m is the current volumetric flow rate of the pump, expressed in m³. 3 / s; β is the differential pressure control ratio, which is the ratio of the system control differential pressure to the system rated differential pressure. The value of β varies depending on the control point; n is the flow rate exponent under different differential pressure control ratios β; b i The coefficients are the model fitting coefficients, i = 1, 2; Step four specifically includes: firstly, using the approximation degree, wet-bulb temperature, cooling water flow rate, and actual operating air volume of the cooling tower fan, an approximation degree model of the cooling tower is established by identifying characteristic coefficients, as shown in equation (9). In the formula, T app The approximation degree of the cooling tower is expressed in °C; ΔT cw The temperature difference between the inlet and outlet of the cooling water, in °C; T wb Outdoor wet-bulb temperature, °C; m cw The cooling water flow rate is m 3 / h;m a The actual air volume of the cooling tower fan is in meters. 3 / h;d i These are the model fitting coefficients, i = 1, 2, 3…; The actual operating air volume ratio of the cooling tower under any operating condition is calculated based on the approximation model. The energy consumption model of the cooling tower is established by identifying characteristic coefficients through the actual air volume ratio and power ratio. The real-time energy consumption of the cooling tower under any operating condition is calculated based on the energy consumption model of the cooling tower.

2. The energy-saving method for a central air conditioning system based on intelligent control according to claim 1, characterized in that: In step one, the actual operating data of the central air conditioning system is statistically analyzed and preprocessed. This involves statistically analyzing the actual operating data and calculating the chiller COP. Abnormal data such as imbalance rate exceeding 15%, COP values ​​outside the range of (μ-3σ, μ+3σ), and chilled water pump and cooling water pump operating frequencies below 30Hz and above 50Hz are removed. Here, μ and σ are the average and standard deviation of COP in all data, respectively.

3. The energy-saving method for a central air conditioning system based on intelligent control according to claim 1, characterized in that: In step two, a COP performance model of the chiller unit is established based on data-driven and mechanistic framework. By using the chilled water supply temperature, cooling water return temperature, central air conditioning system cooling load and the measured COP of the chiller unit, the COP performance model of the chiller unit is established using the characteristic coefficient identification method. Based on this model, the COP of the chiller unit under any operating condition can be calculated, and the real-time energy consumption of the chiller unit can be obtained by further calculating the energy consumption formula.

4. The energy-saving method for a central air conditioning system based on intelligent control according to claim 1, characterized in that: In step five, a genetic algorithm is used to optimize the main control variables of the total energy consumption of the central air conditioning system. Based on the energy consumption model built in steps two, three and four, the coupling and constraint relationships between the energy-consuming equipment models are constructed. Finally, based on the genetic algorithm, with the goal of minimizing the total energy consumption of the central air conditioning system, real-time optimization calculation is performed to obtain the optimal system control parameters and issue control commands to the system to reduce the energy consumption of the central air conditioning system.

Images