Air conditioning system and control method thereof

Abstract

The application provides an air conditioning system and a control method thereof, relates to the technical field of household appliances, and is used for improving the prediction accuracy of the performance ratio of the air conditioning system, thereby effectively reducing the operation energy consumption of the air conditioning system. The air conditioning system comprises an evaporator, a condenser and a controller. The controller is configured to: acquire the evaporating temperature, the condensing temperature, the first energy efficiency ratio and the load rate of the air conditioning system according to the operation data of the evaporator and the condenser within a preset time length; acquire the second energy efficiency ratio of the air conditioning system and the first corresponding relationship between the second energy efficiency ratio and the load rate of the air conditioning system according to the evaporating temperature, the condensing temperature, the first energy efficiency ratio and the load rate; acquire the second corresponding relationship between the second energy efficiency ratio and the load rate of the air conditioning system by using a back propagation neural network model; and acquire the third corresponding relationship between the target energy efficiency ratio of the air conditioning system and the load rate of the air conditioning system by using the first corresponding relationship and the second corresponding relationship based on a mean value clustering algorithm.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of household appliances, and in particular to an air conditioning system and a control method thereof. BACKGROUND

[0002] In the related art, the energy efficiency ratio of an air conditioning system can be determined by establishing a performance model of the air conditioning system, so as to further determine the refrigerating capacity of the air conditioning system according to the energy efficiency ratio. The performance model of the air conditioning system is generally established in a laboratory. Specifically, the cooling water inlet temperature can be adjusted under different load rates of different air conditioning systems by taking advantage of the convenience of the laboratory, so that the COP (energy efficiency ratio) of the air conditioning system is always maintained in a higher range.

[0003] However, the environment in which the air conditioning system is actually applied is quite different from the laboratory environment. The performance model of the air conditioning system determined in the laboratory does not conform to the actual situation in the actual application. The refrigerating capacity determined by using such a performance model in the actual application has a relatively large deviation from the actual refrigerating capacity. The refrigeration performed according to such a refrigerating capacity may increase energy consumption. SUMMARY

[0004] The embodiments of the present application provide an air conditioning system and a control method thereof, which can reflect the actual performance of the air conditioning system under different load rates, improve the prediction accuracy of the energy efficiency ratio of the air conditioning system, and thus effectively reduce the operating energy consumption of the air conditioning system.

[0005] In a first aspect, the present application provides an air conditioning system, which comprises:

[0006] an evaporator configured to convert refrigerant from a normal-temperature liquid state to a low-temperature gaseous state to achieve a refrigeration purpose;

[0007] a condenser configured to convert refrigerant from a high-temperature gaseous state to a normal-temperature liquid state to achieve a heating purpose;

[0008] a controller electrically connected to the evaporator and the condenser, the controller being configured to:

[0009] obtain an evaporating temperature, a condensing temperature, a first energy efficiency ratio, and a load rate of the air conditioning system according to operating data of the evaporator and the condenser within a preset time period;

[0010] obtain a second energy efficiency ratio of the air conditioning system and a first correspondence relationship between the second energy efficiency ratio and the load rate of the air conditioning system according to the evaporating temperature, the condensing temperature, the first energy efficiency ratio, and the load rate;

[0011] obtain a second correspondence relationship between the second energy efficiency ratio and the load rate of the air conditioning system by using a back propagation neural network model; and

[0012] The third corresponding relationship between the target energy efficiency ratio of the air conditioning system and the load ratio of the air conditioning system is obtained based on the mean clustering algorithm and the first corresponding relationship and the second corresponding relationship.

[0013] The technical scheme provided in the application brings at least the following beneficial effects: the first energy efficiency ratio and the second energy efficiency ratio of the air conditioning system are obtained according to the operation data of the evaporator and the condenser in the preset time period, and the first corresponding relationship between the second energy efficiency ratio and the load ratio of the air conditioning system is established. Then, the second corresponding relationship between the second energy efficiency ratio and the load ratio of the air conditioning system is predicted through the back propagation neural network model. Then, it is determined whether the third corresponding relationship is established according to the first corresponding relationship or the second corresponding relationship based on the mean clustering algorithm. The control method of the application can obtain multiple corresponding relationships between the energy efficiency ratio of the air conditioning system and the load ratio of the air conditioning system in different ways, and select a more suitable corresponding relationship to determine the target energy efficiency ratio. According to the target energy efficiency ratio, a more accurate refrigerating capacity can also be determined, thereby reducing the operation energy consumption of the air conditioning system. Moreover, the prediction accuracy of the energy efficiency ratio of the air conditioning system is improved, and the problem of low prediction accuracy of the energy efficiency ratio of the traditional air conditioning system performance model is solved. At the same time, it also provides a premise for the energy consumption simulation, energy efficiency monitoring and development of reasonable energy-saving control strategies of the air conditioning system.

[0014] In some embodiments, the operation data of the evaporator and the condenser in the preset time period includes the chilled water supply temperature, the chilled water return temperature, the chilled water flow and the evaporator evaporation temperature of the evaporator, the cooling water supply temperature, the cooling water return temperature, the cooling water flow and the condenser condensation temperature of the condenser, the cold machine load ratio and the cold machine power of the air conditioning system; wherein the operation data corresponding to each time point in the preset time period constitutes a data group. In this embodiment, the operation data of the evaporator and the condenser in the preset time period can be the operation data of each period throughout the year, and the time lines of all data are unified. Using such operation data can more comprehensively and accurately establish the corresponding relationship between the energy efficiency ratio of the air conditioning system and the load ratio of the air conditioning system, thereby improving the prediction accuracy of the energy efficiency ratio of the air conditioning system.

[0015] In some embodiments, the controller of the air conditioning system is configured to obtain the evaporating temperature of the air conditioning system, including: obtaining the direct load of the chiller according to the specific heat capacity of water and the chilled water flow, the chilled water return temperature and the chilled water supply temperature in the target data group in the operation data; obtaining the cooling capacity of the chiller according to the specific heat capacity of water and the cooling water flow, the cooling water return temperature and the cooling water supply temperature in the target data group in the operation data; obtaining the logarithmic mean temperature difference of the evaporator corresponding to the target data group according to the temperature difference between the chilled water supply temperature in the target data group and the evaporating temperature of the evaporator, and the temperature difference between the chilled water return temperature in the target data group and the evaporating temperature of the evaporator; obtaining the heat transfer coefficient of the evaporator corresponding to the target data group according to the direct load of the chiller and the logarithmic mean temperature difference of the evaporator; fitting to obtain the target heat transfer coefficient of the evaporator according to the heat transfer coefficients of the evaporators corresponding to different data groups; and obtaining the evaporating temperature of the air conditioning system according to the density of water, the specific heat capacity of water, the target heat transfer coefficient of the evaporator, the direct load of the chiller, the chilled water flow and the chilled water supply temperature. In this embodiment, the target heat transfer coefficient of the evaporator is fitted according to the heat transfer coefficients of the evaporators corresponding to different data groups in the operation data, so that the obtained evaporating temperature data of the air conditioning system is more comprehensive and accurate.

[0016] In some embodiments, the controller of the air conditioning system is configured to obtain the condensing temperature of the air conditioning system, including: obtaining the direct load of the chiller according to the specific heat capacity of water and the chilled water flow, the chilled water return temperature and the chilled water supply temperature in the target data group in the operation data; obtaining the cooling capacity of the chiller according to the specific heat capacity of water and the cooling water flow, the cooling water return temperature and the cooling water supply temperature in the target data group in the operation data; obtaining the logarithmic mean temperature difference of the condenser corresponding to the target data group according to the temperature difference between the cooling water supply temperature in the target data group and the condensing temperature of the condenser, and the temperature difference between the cooling water return temperature in the target data group and the condensing temperature of the condenser; obtaining the heat transfer coefficient of the condenser corresponding to the target data group according to the direct load of the chiller and the logarithmic mean temperature difference of the condenser; fitting to obtain the target heat transfer coefficient of the condenser according to the heat transfer coefficients of the condensers corresponding to different data groups; and obtaining the condensing temperature of the air conditioning system according to the density of water, the specific heat capacity of water, the target heat transfer coefficient of the condenser, the direct load of the chiller, the cooling water flow and the cooling water return temperature. In this embodiment, the target heat transfer coefficient of the condenser is fitted according to the heat transfer coefficients of the condensers corresponding to different data groups in the operation data, so that the obtained condensing temperature data of the air conditioning system is more comprehensive and accurate.

[0017] In some embodiments, the controller of the air conditioning system is further configured to: obtain a load imbalance rate according to the direct load of the cold machine, the cooling capacity of the cold machine, and the cold machine power in the target data group in the operation data; and delete the data in the target data group in the operation data when the load imbalance rate is greater than or equal to a preset imbalance rate. In this embodiment, the load imbalance rate is obtained according to the cold machine power, the direct load of the cold machine, and the cooling capacity of the cold machine, and the data group corresponding to the abnormal load imbalance rate in the operation data is deleted, so that the data in the operation data is more accurate, and a foundation is laid for subsequent improvement of the prediction accuracy of the energy efficiency ratio of the air conditioning system.

[0018] In some embodiments, the controller of the air conditioning system is configured to obtain a first energy efficiency ratio of the air conditioning system, including: obtaining the first energy efficiency ratio of the air conditioning system according to the direct load of the cold machine and the cold machine power in the target data group in the operation data; and deleting the data in the target data group in the operation data when the first energy efficiency ratio is outside a preset interval. In this embodiment, the data group corresponding to the abnormal first energy efficiency ratio in the operation data is deleted, so that the data in the operation data is more accurate, and a foundation is laid for subsequent improvement of the prediction accuracy of the energy efficiency ratio of the air conditioning system.

[0019] In some embodiments, the controller of the air conditioning system is further configured to: obtain a second energy efficiency ratio of the air conditioning system and a first correspondence relationship between the second energy efficiency ratio and the load rate of the air conditioning system according to the evaporation temperature, the condensation temperature, the first energy efficiency ratio, and the load rate, including: obtaining the second energy efficiency ratio of the air conditioning system according to the evaporation temperature, the condensation temperature, the first energy efficiency ratio, and the load rate; and generating a scatter plot composed of a plurality of data points by taking the second energy efficiency ratio as the horizontal coordinate and taking the load rate corresponding to the second energy efficiency ratio as the vertical coordinate; wherein each data point corresponds to one second energy efficiency ratio and one load rate. In this embodiment, the first correspondence relationship obtained in the form of a curve can represent the performance model of the air conditioning system, and the model is established according to actual operation data. The air conditioning system performance model curve obtained based on a large amount of actual operation data is one of the bases for optimizing the operation of the air conditioning system, and the air conditioning system performance model obtained by using this method is more complete, so that it can be selectively applied to air conditioning systems in different actual environments, and the prediction accuracy of the energy efficiency ratio of the air conditioning system is improved.

[0020] In some embodiments, the controller of the air conditioning system is configured to obtain the second correspondence between the second energy efficiency ratio and the load ratio of the air conditioning system by using the back propagation neural network model, including: inputting the cooling load ratio in the operation data and the temperature difference between the evaporation temperature and the condensation temperature of the air conditioning system into the back propagation neural network model to obtain the second energy efficiency ratio and the second correspondence between the second energy efficiency ratio and the load ratio of the air conditioning system. In this embodiment, the back propagation neural network model can also be used to obtain the second correspondence between the second energy efficiency ratio and the load ratio of the air conditioning system, which can be regarded as an air conditioning system performance prediction model. The back propagation neural network model can automatically extract the "reasonable" solution rule by learning the instance set with correct answers, that is, it has self-learning ability and is suitable for solving problems with complex internal mechanisms. The air conditioning system performance prediction model obtained by using this method makes the construction of the air conditioning system performance model more complete, so that it can be selectively applied to air conditioning systems in different actual environments and improve the prediction accuracy of the energy efficiency ratio of the air conditioning system.

[0021] In some embodiments, the controller of the air conditioning system is configured to obtain the third correspondence between the target energy efficiency ratio of the air conditioning system and the load ratio of the air conditioning system by using the first correspondence and the second correspondence based on the mean clustering algorithm, including: obtaining the data similarity between the current data set and the target data set in the operation data based on the cooling load ratio, the temperature difference between the evaporation temperature and the condensation temperature of the air conditioning system; the current data set includes the operation data obtained after a preset time length; in the case that the data similarity is less than or equal to a preset similarity, the third correspondence is established according to the first correspondence; in the case that the data similarity is greater than the preset similarity, the third correspondence is established according to the second correspondence. In this embodiment, the data similarity between the first data set and the current data set is obtained by using the mean clustering algorithm, and the third correspondence is established by using the first or second correspondence according to the size of the similarity, so that the establishment of the air conditioning system performance model is based on the actual situation of the current data, which improves the prediction accuracy of the air conditioning system model and realizes the efficient, safe and energy-saving operation of the air conditioning system.

[0022] In a second aspect, the present application provides a control method of an air conditioning system. The method is applied to the air conditioning system of the first aspect. The method includes: obtaining the evaporation temperature, the condensation temperature, the first energy efficiency ratio and the load ratio of the air conditioning system according to the operation data of the evaporator and the condenser within a preset time length; obtaining the second energy efficiency ratio of the air conditioning system and the first correspondence between the second energy efficiency ratio and the load ratio of the air conditioning system according to the evaporation temperature, the condensation temperature, the first energy efficiency ratio and the load ratio; obtaining the second correspondence between the second energy efficiency ratio and the load ratio of the air conditioning system by using the back propagation neural network model; and obtaining the third correspondence between the target energy efficiency ratio of the air conditioning system and the load ratio of the air conditioning system by using the first correspondence and the second correspondence based on the mean clustering algorithm.

[0023] In a third aspect, the present application provides a controller, comprising: one or more processors; one or more memories; wherein the one or more memories are configured to store computer program codes, the computer program codes comprising computer instructions, when the one or more processors execute the computer instructions, the controller executes the control method of the air conditioning system provided in the second aspect and possible implementation manners.

[0024] In a fourth aspect, the present application provides a computer readable storage medium, the computer readable storage medium comprising computer instructions, when the computer instructions are run on a computer, the computer instructions cause the computer to execute the control method of the air conditioning system provided in the second aspect and possible implementation manners.

[0025] In a fifth aspect, the present application provides a computer program product, the computer program product can be directly loaded into a memory and contains software codes, and the computer program product, when loaded and executed by a computer, can realize the control method of the air conditioning system provided in the second aspect and possible implementation manners.

[0026] It should be noted that the above computer instructions can be stored in the computer readable storage medium in whole or in part. The computer readable storage medium can be packaged together with the processor of the controller, or can be packaged separately from the processor of the controller, and the present application does not limit this.

[0027] The beneficial effects of the second aspect to the fifth aspect of the present application are described above, and the beneficial effects of the first aspect are not repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0028] Figure 1 A structural schematic diagram of an air conditioning system provided by an embodiment of the present application is shown in FIG. 1;

[0029] Figure 2 A hardware configuration diagram of an air conditioning system provided by an embodiment of the present application is shown in FIG. 2;

[0030] Figure 3 A flowchart of a control method of an air conditioning system provided by an embodiment of the present application is shown in FIG. 3;

[0031] Figure 4 A flowchart of another control method of an air conditioning system provided by an embodiment of the present application is shown in FIG. 4;

[0032] Figure 5 A flowchart of another control method of an air conditioning system provided by an embodiment of the present application is shown in FIG. 5;

[0033] Figure 6 A flowchart of another control method of an air conditioning system provided by an embodiment of the present application is shown in FIG. 6;

[0034] Figure 7 A flowchart of another control method of an air conditioning system provided by an embodiment of the present application is shown in FIG. 6;

[0035] Figure 8 A flowchart of another control method of an air conditioning system provided by an embodiment of the present application is shown in FIG. 6;

[0036] Figure 9 A flowchart of another control method of an air conditioning system provided by an embodiment of the present application is shown in FIG. 6;

[0037] Figure 10 A flowchart of another control method of an air conditioning system provided by an embodiment of the present application is shown in FIG. 6;

[0038] Figure 11 A result graph of calculation of evaporation temperature and condensation temperature of a cold machine provided by an embodiment of the present application is shown in FIG. 7;

[0039] Figure 12 A result graph of prediction of new data of a cold machine performance model provided by an embodiment of the present application is shown in FIG. 8;

[0040] Figure 13 A neural network structure graph of a cold machine performance prediction model provided by an embodiment of the present application is shown in FIG. 9;

[0041] Figure 14 A result graph of prediction of new data of another cold machine performance model provided by an embodiment of the present application is shown in FIG. 10;

[0042] Figure 15 A result graph of prediction of new data of a cold machine model provided by an embodiment of the present application is shown in FIG. 11;

[0043] Figure 16 A hardware structure schematic diagram of a controller provided by an embodiment of the present application is shown in FIG. 12. DETAILED DESCRIPTION

[0044] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0045] The terms "first", "second" are only used for description purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "multiple" is two or more.

[0046] In the description of the present application, it should be noted that unless specifically defined and limited, the terms "connected", "connected" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances. In addition, when describing the pipeline, "connected" and "connected" in the present application have the meaning of conducting. The specific meaning should be understood in combination with the context.

[0047] In the embodiments of the present application, the words such as "exemplary" or "for example" are used to represent as an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "exemplary" or "for example" are intended to present the relevant concept in a specific manner.

[0048] In the related art, the energy efficiency ratio of the air conditioning system can generally be determined by establishing a performance model of the air conditioning system, so as to further determine the refrigerating capacity of the air conditioning system according to the energy efficiency ratio. The performance model of the air conditioning system is generally established in the laboratory. Specifically, the convenience of the laboratory can be used to adjust different cooling water inlet temperatures under different load rates of the air conditioning system, so as to maintain the COP (energy efficiency ratio) of the air conditioning system in a higher range. However, in actual application, the environment of the air conditioning system is quite different from the laboratory environment. The performance model of the air conditioning system determined in the laboratory does not conform to the actual situation in actual application. The deviation of the refrigerating capacity determined by using such performance model in actual application from the actual refrigerating capacity is relatively large. The refrigeration according to such refrigerating capacity may increase energy consumption.

[0049] Based on the above, the embodiments of the present application provide an air conditioning system and a control method thereof. The air conditioning system can obtain a plurality of corresponding relationships between the energy efficiency ratio of the air conditioning system and the load rate of the air conditioning system in different ways, and selectively use a certain corresponding relationship to determine the target energy efficiency ratio of the air conditioning system according to the actual situation of the current running data of the air conditioning system, so as to accurately determine the refrigerating capacity of the air conditioning system and the like according to the target energy efficiency ratio. In this way, the problem of low prediction accuracy of the traditional performance model of the air conditioning system is solved. It provides a premise for energy consumption simulation, energy efficiency monitoring and formulating a reasonable energy-saving control strategy of the air conditioning system.

[0050] Among them, the air conditioning system can also be called a cold machine, and the performance model of the air conditioning system can also be called a cold machine performance model.

[0051] Figure 1 The structure schematic diagram of the air conditioning system 11 provided in the present application is shown in the figure. As shown inFigure 1 As shown, the air conditioning system 11 includes: a condenser 100, an evaporator 101, a compressor 102, and an expansion valve 103.

[0052] In some embodiments, the condenser 100, evaporator 101, compressor 102, and expansion valve 103 constitute a closed-loop refrigerant circulation loop.

[0053] In some embodiments, the condenser 100 can be a shell-and-tube condenser, a spiral plate condenser, or a strip condenser, etc. The working principle of the condenser 100 is that after the high-pressure superheated gaseous refrigerant from the refrigeration compressor enters the condenser, it transfers heat to the surrounding air, or first transfers heat to water, and then the water transfers heat to the surrounding air. While the refrigerant releases heat in the condenser, it condenses into a liquid due to cooling.

[0054] In some embodiments, the evaporator 101 can be a shell-and-tube evaporator, a water tank evaporator, etc. The working principle of the evaporator 101 is that the liquid refrigerant absorbs the heat energy of the object being cooled by water in the evaporator and evaporates into gaseous refrigerant.

[0055] In some embodiments, compressor 102 may be a centrifugal compressor, screw compressor, scroll compressor, etc. Compressor 102 is used to increase the pressure of refrigerant in the air conditioning refrigeration system, so that the refrigerant circulates in the air conditioning refrigeration system to achieve the purpose of refrigeration.

[0056] In some embodiments, the expansion valve 103 may be a thermostatic expansion valve. The expansion valve 103 is located at the outlet of the condenser 100 and the inlet of the evaporator 101, and is used to reduce the condensing pressure of the refrigerant to the evaporating pressure.

[0057] like Figure 2 As shown, the air conditioning system 11 also includes one or more of the following: a controller 104, a sensor module 105, and a power supply 106. The controller 104, sensor module 105, and power supply 106 are all connected to the controller 104.

[0058] In some embodiments, the controller 104 is used to generate an operation control signal based on the instruction opcode and timing signal, instructing the air conditioning system to execute control commands. For example, the controller 104 issues control commands to acquire the evaporation temperature, condensation temperature, operating data, etc. of the air conditioning system 11.

[0059] In some embodiments, the controller 104 can acquire the operating data of the air conditioning system 11 through the sensor module 105.

[0060] In some embodiments, the power supply 106 is configured to provide operating power support for various electrical components of the air conditioning system 11 under the control of the controller 104. The power supply 106 can include a battery and related control circuitry.

[0061] Based on the above air conditioning system, as Figure 3 shown, the embodiments of the present application provide a control method of an air conditioning system, which can include the following steps:

[0062] S101, the air conditioning system obtains the evaporating temperature, the condensing temperature, the first energy efficiency ratio and the load rate of the air conditioning system according to the operation data of the evaporator and the condenser within a preset time period.

[0063] In some embodiments, the operation data includes the chilled water supply temperature, the chilled water return temperature, the chilled water flow rate and the evaporator evaporating temperature of the evaporator, the cooling water supply temperature, the cooling water return temperature, the cooling water flow rate and the condenser condensing temperature of the condenser, the chiller load rate and the chiller power of the air conditioning system, etc.

[0064] In some embodiments, part of the operation data of the air conditioning system can be obtained by installing a sensor.

[0065] For example, the chilled water supply temperature, the chilled water return temperature, the chilled water flow rate and the evaporator evaporating temperature of the evaporator, the cooling water supply temperature, the cooling water return temperature, the cooling water flow rate and the condenser condensing temperature of the condenser, etc. can be obtained by installing a temperature sensor. The preset time period can be half a year, one year, etc., wherein the operation data corresponding to each time point within the preset time period can form a data set, and the time interval for obtaining the operation data can be 5 minutes, 10 minutes, etc. For example, a data set can be obtained every 5 minutes, and the data set can include the chilled water supply temperature, the chilled water return temperature, the chilled water flow rate and the evaporator evaporating temperature of the evaporator, the cooling water supply temperature, the cooling water return temperature, the cooling water flow rate and the condenser condensing temperature of the condenser, the chiller load rate and the chiller power of the air conditioning system at the time point.

[0066] In some embodiments, the first energy efficiency ratio can be represented as COP (Coefficient Of Performance, refrigeration performance coefficient), which refers to the refrigeration capacity obtained per unit power consumption, and is an important technical and economic indicator of the air conditioning system (e.g. chiller). The larger the refrigeration performance coefficient, the higher the energy utilization efficiency of the air conditioning system.

[0067] S102, the air conditioning system obtains the second energy efficiency ratio and the first correspondence relationship between the second energy efficiency ratio and the load rate of the air conditioning system through the evaporating temperature, the condensing temperature and the first energy efficiency ratio.

[0068] In some embodiments, the second energy efficiency ratio is DCOP (cooling performance coefficient), which also represents the internal energy efficiency of the air conditioning system, and mainly reflects the deviation between COP and ICOP (ideal COP value). Through the DCOP, the cause of low running efficiency of the air conditioning system can be determined.

[0069] In some embodiments, the first correspondence relationship can be an air conditioning system DCOP performance model established between the DCOP of the air conditioning system and the PLR (Part Load Ratio) of the air conditioning system. Since the first correspondence relationship is obtained or established based on actual operation data, the DCOP performance model corresponding to the first correspondence relationship can reflect the real energy efficiency of the air conditioning system.

[0070] S103, the air conditioning system obtains a second correspondence relationship between the second energy efficiency ratio and the load ratio of the air conditioning system by using the back propagation neural network model.

[0071] In some embodiments, the second correspondence relationship can be an air conditioning system DCOP performance prediction model established between the DCOP of the air conditioning system and the PLR of the air conditioning system. Since the second correspondence relationship is established through the learning and prediction of the back propagation neural network, the DCOP performance prediction model corresponding to the second correspondence relationship can predict the energy efficiency of the air conditioning system.

[0072] In some embodiments, the back propagation neural network model is a BP (Back Propagation) neural network structure. The BP neural network is a multi-layer feedforward neural network trained according to the error back propagation algorithm, and is the most widely used neural network. The BP neural network is the most commonly used and best effective model for modeling non-linear, non-periodic, irregular, non-structural or semi-structural data. The BP neural network prediction model with time series characteristics established by combining data mining is a very suitable method for air conditioning system performance prediction.

[0073] In some embodiments, the cooling load rate of the air conditioning system in the running data, and the temperature difference between the evaporating temperature and the condensing temperature of the air conditioning system can be input into the back propagation neural network model to obtain a second energy efficiency ratio and a second correspondence between the second energy efficiency ratio and the load rate of the air conditioning system. For example, a BP neural network structure is established, which has three layers in total, the input neurons of the neural network are: the cooling load rate, and the difference between the condensing temperature and the evaporating temperature; the number of network nodes of the network hidden layer is 7; and the output neuron is DCOP. The BP neural network model uses the trainlm (Levenberg-Marquarelt) learning algorithm, the transfer function of the network hidden layer selects the tansig function (bipolar S function), the output layer selects the Pureline function (linear function), the learning rate of the BP neural network model can be set to 0.05, the maximum learning step can be set to 1000 times, and the training target error can be set to 0.003, so that the above-mentioned DCOP performance prediction model can be obtained through data training.

[0074] In S104, the air conditioning system obtains a third correspondence between the target energy efficiency ratio of the air conditioning system and the load rate of the air conditioning system based on the mean value clustering algorithm and the first correspondence and the second correspondence.

[0075] In some embodiments, the third correspondence represents a target performance model of the air conditioning system that can obtain the target energy efficiency ratio.

[0076] In some embodiments, the mean value clustering algorithm is a K-means (K-means clustering algorithm) clustering algorithm. The K-means algorithm is a classic distance-based clustering algorithm that uses distance as an evaluation indicator of similarity, that is, two objects are considered to be more similar if they are closer in distance. As one of the simplest and fastest clustering algorithms, the K-means clustering algorithm has a large and wide range of uses. Based on the mean value clustering algorithm, it can be determined whether to establish the third correspondence according to the first correspondence or the second correspondence.

[0077] In some embodiments, according to the first correspondence, the third correspondence can be established according to the DCOP performance model established by using the real running data of the air conditioning system to predict the performance of the air conditioning system in the current time, and the performance can be represented by the target energy efficiency ratio; according to the second correspondence, the third correspondence can be established according to the DCOP performance prediction model of the air conditioning system established by the BP neural network to predict the performance of the air conditioning system in the current time, and the performance can be represented by the target energy efficiency ratio.

[0078] The foregoing embodiments at least have the following beneficial effects: according to the operation data of the evaporator and the condenser within the preset time length, the first energy efficiency ratio and the second energy efficiency ratio of the air conditioning system are obtained, and a first corresponding relationship between the second energy efficiency ratio and the load rate of the air conditioning system is established. Then, the second corresponding relationship between the second energy efficiency ratio and the load rate of the air conditioning system is predicted through the back propagation neural network model. Whether the third corresponding relationship is established according to the first corresponding relationship or the second corresponding relationship is determined based on the mean clustering algorithm. The control method of the application can obtain multiple corresponding relationships between the energy efficiency ratio of the air conditioning system and the load rate of the air conditioning system in different ways, and select a more appropriate corresponding relationship to determine the target energy efficiency ratio. According to the target energy efficiency ratio, a more accurate refrigerating capacity can be determined, so as to reduce the operation energy consumption of the air conditioning system. In this way, the prediction accuracy of the energy efficiency ratio of the air conditioning system can be improved, and the problem of low prediction accuracy of the energy efficiency ratio of the traditional air conditioning system performance model is solved. At the same time, it provides a premise for the energy consumption simulation, energy efficiency monitoring and reasonable energy-saving control strategy of the air conditioning system.

[0079] In some embodiments, the first performance ratio of the air conditioning system, the evaporating temperature and the cooling temperature can be further obtained by obtaining the chiller direct load and the chiller cooling capacity. Therefore, as shown in FIG. 1, the step S101 can specifically include the following steps: Figure 4

[0080] S201, obtaining the chiller direct load according to the specific heat capacity of water and the chilled water flow, the chilled water return water temperature and the chilled water supply water temperature in the target data group in the operation data.

[0081] In some embodiments, the chiller direct load can be obtained by using formula (1):

[0082] Q d = c·m e ·(T e-rtn -T e-sup ) (1)

[0083] In the formula, Q d represents the chiller direct load; c represents the specific heat capacity of water; m e represents the chilled water mass flow; T e-rtn represents the chilled water return water temperature; and T e-sup represents the chilled water supply water temperature.

[0084] S202, obtaining the chiller cooling capacity according to the specific heat capacity of water and the cooling water flow, the cooling water return water temperature and the cooling water supply water temperature in the target data group in the operation data.

[0085] In some embodiments, the chiller cooling capacity can be obtained by using formula (2):

[0086] ​Q c =c·m c ·(T c-sup -T c-rtn (2)

[0087] In the formula: Q c Indicates the cooling capacity of the chiller; m c Indicates cooling water flow rate; T c-sup Indicates the cooling water supply temperature; T c-rtn This indicates the return temperature of the cooling water.

[0088] In some embodiments, considering the errors in time measurement, the load imbalance rate can be obtained based on the chiller power, chiller direct load, and chiller cooling capacity. If the load imbalance rate is greater than or equal to a preset load imbalance rate, the data group corresponding to that load imbalance rate in the operating data is deleted to reduce data acquisition errors. For example, the load imbalance rate can be calculated using formula (3):

[0089]

[0090] In the formula: B a P represents the load imbalance rate; w This indicates the chiller power.

[0091] For example, the preset load imbalance rate can be 15%. That is, when the load imbalance rate calculated based on some data in a set of data is greater than or equal to 15%, all data in the data set corresponding to the load imbalance rate are removed from the operating data.

[0092] In the above embodiments, the data groups corresponding to abnormal load imbalance rates in the operating data are removed, thereby reducing the interference of abnormal data groups on the establishment of the air conditioning system performance model, making the data groups in the operating data more accurate, and laying the foundation for improving the accuracy of the air conditioning system model in the future.

[0093] In some embodiments, such as Figure 5 As shown, removing the data group corresponding to the abnormal data value of the first energy efficiency ratio may include the following steps:

[0094] S301. Obtain the first energy efficiency ratio of the air conditioning system based on the chiller direct load and the chiller power in the target data group of the operating data.

[0095] In some embodiments, the chiller cooling capacity can be obtained using formula (4):

[0096]

[0097] In the formula: COP represents the first energy efficiency ratio.

[0098] S302, in the case that the first energy efficiency ratio is outside the preset interval, deleting data in the target data group from the running data.

[0099] For example, the preset interval can be (μ1-2σ1, μ1+2σ1), where μ1 is the average value of the COP of the month, and σ1 is the standard deviation of the COP of the month. That is, when the COP value is outside the interval (μ1-2σ1, μ1+2σ1), it is an abnormal value, and all data in the target data group corresponding to the COP value are deleted from the running data.

[0100] In the above embodiment, in the case that the first energy efficiency ratio is outside the preset interval, the data group corresponding to the first energy efficiency ratio in the running data is deleted. In this embodiment, the data group corresponding to the abnormal first energy efficiency ratio in the running data is deleted, thereby reducing the interference of the abnormal data group on the establishment of the performance model of the air conditioning system, making the data in the running data more accurate, and laying a foundation for improving the accuracy of the air conditioning system model in the subsequent.

[0101] In some embodiments, as shown in Figure 6 The method for obtaining the evaporating temperature of the air conditioning system can include the following steps:

[0102] S401, obtaining the logarithmic mean temperature difference of the evaporator corresponding to the target data group according to the temperature difference between the chilled water supply temperature and the evaporator evaporating temperature in the target data group, and the temperature difference between the chilled water return temperature and the evaporator evaporating temperature in the target data group.

[0103] In some embodiments, the logarithmic mean temperature difference of the evaporator can be obtained by using formulas (5) and (6):

[0104]

[0105] Δt ch,e = Δt e2 - Δt e1 (6)

[0106] In the formula, Δte2 and Δte1 respectively represent the temperature difference between the chilled water supply temperature and the evaporator evaporating temperature, and the temperature difference between the chilled water return temperature and the evaporator evaporating temperature; Δt m,e represents the logarithmic mean temperature difference of the evaporator; and Δt ch,e represents the evaporator inlet and outlet temperature difference.

[0107] S402, obtaining the heat transfer coefficient of the evaporator corresponding to the target data group according to the direct cooling load and the logarithmic mean temperature difference of the evaporator.

[0108] In some embodiments, the heat transfer coefficient of the evaporator can be obtained by using formula (7):

[0109]

[0110] K e F e represents the evaporator heat transfer coefficient.

[0111] S403, according to the evaporator heat transfer coefficient corresponding to different data groups, fitting the target heat transfer coefficient of the evaporator.

[0112] In some embodiments, the target heat transfer coefficient of the evaporator can be obtained by regression fitting formula (8):

[0113]

[0114] In the formula: a1, b1, c1, d1, e1, f1 represents the fitting of the evaporator model each term parameter.

[0115] In some embodiments, the target heat transfer coefficient of the evaporator is obtained by regression fitting, which can quantitatively describe the evaporation temperature of the air conditioning system in a curve way, so that the evaporation temperature of the air conditioning system is more comprehensive and accurate.

[0116] S404, according to the density of water, the specific heat capacity of water, the target heat transfer coefficient of the evaporator, the direct load of the cold machine, the chilled water flow and the chilled water supply temperature, the evaporation temperature of the air conditioning system is obtained.

[0117] In some embodiments, the evaporation temperature of the air conditioning system can be obtained by formula (9):

[0118]

[0119] In the formula: ρ represents the density of water; T e represents the evaporation temperature.

[0120] In the above embodiments, according to the evaporator heat transfer coefficient corresponding to different data groups in the running data, the target heat transfer coefficient of the evaporator is fitted, which can help to establish the heat transfer model of the evaporator, so that the evaporation temperature data of the air conditioning system obtained is more comprehensive and accurate.

[0121] In some embodiments, as Figure 7 shown, obtaining the condensing temperature of the air conditioning system can include the following steps:

[0122] S501, according to the temperature difference between the cooling water supply temperature and the condenser condensing temperature in the target data group, and the temperature difference between the cooling water return temperature and the condenser condensing temperature in the target data group, the logarithmic mean temperature difference of the condenser corresponding to the target data group is obtained.

[0123] In some embodiments, the logarithmic mean temperature difference of the condenser can be obtained by formula (10), (11):

[0124]

[0125] Δt ch,c = Δt c2 - Δt c1 (11)

[0126] In the formula, Δtc2 and Δtc1 respectively represent the temperature difference between the outlet temperature of the cooling water and the condenser condensing temperature, and the temperature difference between the return temperature of the cooling water and the condenser condensing temperature; Δt m,c represents the logarithmic mean temperature difference of the condenser; and Δt ch,c represents the temperature difference between the inlet and outlet of the condenser.

[0127] S502, obtaining the condenser heat transfer coefficient corresponding to the target data group according to the direct cooling load and the logarithmic mean temperature difference of the condenser.

[0128] In some embodiments, the condenser heat transfer coefficient can be obtained by using formula (12):

[0129]

[0130] In the formula, K c F c represents the condenser heat transfer coefficient.

[0131] S503, fitting to obtain the target heat transfer coefficient of the condenser according to the condenser heat transfer coefficients corresponding to different data groups.

[0132] In some embodiments, the target heat transfer coefficient of the condenser can be fitted by using formula (13):

[0133]

[0134] In the formula, a2, b2, c2, d2, e2, and f2 represent the parameters of each term of the fitted condenser model.

[0135] In some embodiments, the target heat transfer coefficient of the condenser is obtained by regression fitting, which can quantitatively describe the condensing temperature of the air conditioning system in a curve manner, so that the condensing temperature of the air conditioning system is more comprehensive and accurate.

[0136] S504, obtaining the condensing temperature of the air conditioning system according to the density of water, the specific heat capacity of water, the target heat transfer coefficient of the condenser, the direct cooling load, the cooling water flow rate, and the return temperature of the cooling water.

[0137] In some embodiments, the condensing temperature of the air conditioning system can be obtained by using formula (14):

[0138]

[0139] In the formula, ρ represents the density of water; T c represents the condensing temperature.

[0140] In the above embodiments, the target heat transfer coefficient of the condenser is obtained by fitting according to the heat transfer coefficients of the condenser corresponding to different data groups in the operation data; the heat transfer model of the condenser can be established, so that the obtained condensing temperature data of the air conditioning system is more comprehensive and accurate.

[0141] In some embodiments, the first correspondence between the second energy efficiency ratio and the load rate of the air conditioning system can be a first correspondence of the air conditioning system represented by a curve. Therefore, as shown in Figure 8 The step S102 can specifically include the following steps:

[0142] S601, taking the second energy efficiency ratio as the abscissa and the load rate corresponding to the second energy efficiency ratio as the ordinate, a scatter plot composed of a plurality of data points is generated.

[0143] In some embodiments, the ICOP value of the air conditioning system can be calculated by formula (15), and the DCOP value can be calculated by formula (16):

[0144]

[0145]

[0146] In the formula: ICOP represents the ideal energy efficiency ratio (ideal COP value); DCOP represents the second energy efficiency ratio.

[0147] In some embodiments, the DCOP value can be taken as the abscissa, and the chiller load rate PLR corresponding to the DCOP value can be taken as the ordinate, to generate a scatter plot composed of a plurality of data points. The scatter plot can directly represent the relationship between the DCOP value of the air conditioning system and the corresponding load rate PLR.

[0148] S602, fitting the data points on the scatter plot to obtain a first correspondence represented by a curve.

[0149] In some embodiments, the first correspondence represented by a curve can be an air conditioning system DCOP performance model established by data regression fitting. For example, formula (17) can be used for regression fitting, model coefficients can be identified and obtained, and the air conditioning system DCOP performance model can be obtained:

[0150] DCOP=A·PLR+B·PLR+C (17) 2

[0151] In the formula: PLR is the chiller load rate; A, B and C are the parameters of the fitting air conditioning system model.

[0152] ​In the above embodiment, the DCOP performance model curve of the air conditioning system obtained based on a large amount of actual operation data is one of the bases for optimizing the operation of the air conditioning system, and the DCOP performance model of the air conditioning system obtained by data regression fitting makes the construction of the performance model of the air conditioning system more complete, thereby being selectively applicable to air conditioning systems in different actual environments and improving the prediction accuracy of the energy efficiency ratio of the air conditioning system.

[0153] In some embodiments, a third correspondence relationship of the air conditioning system can be obtained by selectively using the first correspondence relationship or the second correspondence relationship according to the data similarity between the newly added current data group and the target data group in the operation data. Therefore, as shown in FIG. 10, the step S104 can specifically include the following steps: Figure 9

[0154] S701, obtaining the data similarity between the current data group and the target data group in the operation data based on the cold machine load rate, the temperature difference between the evaporation temperature and the condensation temperature of the air conditioning system.

[0155] The current data group includes the operation data obtained after a preset time length, which can also be referred to as the operation data at the current time.

[0156] In the embodiments of the present application, the target data group can represent any one data group in the operation data. In some embodiments, the input data can be clustered by using a K-means clustering analysis method, and the elbow method can be used to find the optimal cluster center number k in a preset interval to obtain cluster centers p1, p2, …, p k For example, the K-means clustering analysis method is used to cluster the cold machine load rate, the temperature difference between the evaporation temperature and the condensation temperature, the elbow method is used to find the optimal cluster center number k in the interval [2, 10], and the cluster centers p1, p2, …, p k Then, the Euclidean distances d1, d2, …, d k between the cold machine load rate, the temperature difference between the evaporation temperature and the condensation temperature, and the cluster centers are calculated by using formula (18):

[0157]

[0158] In the formula, x j is an n-dimensional input parameter, p i is a cluster center, and d i is the Euclidean distance between the input parameter and the cluster center p i .

[0159] In some embodiments, the data similarity can be data proximity, and the data similarity between the current data group and the target data group in the operation data can be calculated by using formula (19):

[0160] ​

[0161] I is the data similarity between the current data set and the target data set in the running data.

[0162] S702, if the data similarity is less than or equal to the preset similarity, the third correspondence relationship is established according to the first correspondence relationship; if the data similarity is greater than the preset similarity, the third correspondence relationship is established according to the second correspondence relationship.

[0163] In some embodiments, the establishment of the third correspondence relationship can also represent the target performance model of the air conditioning system. The target performance model can be obtained by using formula (20), so that the target energy efficiency ratio can be obtained from the target performance model.

[0164] COP = ICOP·DCOP (20)

[0165] The COP in formula (20) can represent the target energy efficiency ratio.

[0166] In some embodiments, the current data set can include the cold machine running load rate, the air conditioning system condensing temperature and the air conditioning system evaporating temperature in the running data obtained after a preset time length. The data of the target data set in the running data is the input neuron in the BP neural network: the cold machine running load rate, the difference between the condensing temperature and the evaporating temperature. The similarity between the current input data and the input neuron in the BP neural network can be calculated by using formula (19), and I'(preset similarity) is used as the boundary. When the similarity is higher than I', it means that the current data set is close to the input neuron in the BP neural network, so the air conditioning system DCOP performance prediction model established by using the BP neural network is selected to establish the target performance model of the air conditioning system; when the similarity is less than or equal to I', it means that the prediction accuracy is higher by using the air conditioning system DCOP performance model, so the air conditioning system DCOP performance model is selected to establish the target performance model of the air conditioning system. In the above embodiments, the data similarity between the first data set and the current data set is obtained by using the mean clustering algorithm, and the third correspondence relationship is established according to the first correspondence relationship or the second correspondence relationship according to the size of the similarity, so that the establishment of the air conditioning system performance model is based on the actual situation of the current data, the prediction accuracy of the air conditioning system model is improved, and a more accurate target energy efficiency ratio and refrigerating capacity can be obtained, so that the efficient, safe and energy-saving operation goal of the air conditioning system can be achieved.

[0167] Hereinafter, the control method in the embodiments of the present application will be described by taking a centrifugal water chiller with a rated refrigerating capacity of 440 kW as an example. The compressor is a centrifugal compressor, the evaporator and the condenser are both shell-and-tube heat exchangers, water flows in the tube, refrigerant R134a flows outside the tube, and an electronic expansion valve is used.

[0168] As Figure 10 shown, the steps of establishing a cold machine performance model are as follows:

[0169] 1. Sensor data collection: Collect a large amount of actual operation data of the cold machine through various sensors to obtain operation data of 10 characteristics, including chilled water supply temperature, chilled water return temperature, cold machine cooling load rate, cold machine power, chilled water flow, cooling water supply temperature, cooling water return temperature, cooling water flow, evaporator evaporation temperature, and condenser condensation temperature in a year.

[0170] 2. Data screening: Screen the data with all data of consecutive months as a group of operation data.

[0171] 1) Calculate the load imbalance rate: Calculate the direct load of the cold machine using formula (1), then calculate the cooling capacity of the cold machine using formula (2), and further calculate the load imbalance rate using formula (3).

[0172] 2) Calculate the COP of the cold machine: Calculate the direct load of the cold machine using formula (1), and further calculate the COP of the cold machine using formula (4).

[0173] 3) Data elimination.

[0174] The identification rules for abnormal imbalance rate are as follows:

[0175] When the imbalance rate exceeds 15%, it is an abnormal value, that is, when the calculated load imbalance rate at a certain time point is greater than or equal to 15%, the data group at the time point corresponding to the load imbalance rate is eliminated from the operation data.

[0176] The identification rules for COP abnormal values are as follows:

[0177] When the COP value is outside the interval (μ1-2σ1, μ1+2σ1), it is an abnormal value, which is eliminated, where μ1 is the average value of the monthly COP, and σ1 is the standard deviation of the monthly COP. That is, when the calculated COP value at a certain time point is outside the interval (μ1-2σ1, μ1+2σ1), it is an abnormal value, and the data group at the time point corresponding to the COP value is eliminated from the operation data.

[0178] 3. Calculate the evaporation temperature and condensation temperature using the data screening value.

[0179] 1) Calculate the evaporation temperature: Calculate the temperature difference between the chilled water supply temperature and the evaporator evaporation temperature, and the temperature difference between the chilled water return temperature and the evaporator evaporation temperature, calculate the logarithmic mean temperature difference of the evaporator and the evaporator inlet and outlet temperature difference respectively through formulas (5) and (6), and then calculate the evaporator heat transfer coefficient K e F eThe evaporator heat transfer coefficient K is quantitatively characterized by regressing and fitting the evaporator heat transfer coefficient K using formula (8) e F e The evaporating temperature is calculated by formula (9). The regressed and fitted coefficients calculated are shown in Table 1 below.

[0180] Table 1: Fitting coefficient calculation results of the evaporator heat transfer model

[0181]

[0182] 2) Calculate the condensing temperature: Calculate the temperature difference between the cooling water return water temperature and the condenser condensing temperature, and the temperature difference between the cooling water outlet water temperature and the condenser condensing temperature, calculate the logarithmic mean temperature difference of the condenser and the temperature difference between the inlet and outlet of the condenser by formula (10), (11) respectively, and then calculate the condenser heat transfer coefficient K by formula (12) c F c The condenser heat transfer coefficient K is quantitatively characterized by regressing and fitting the condenser heat transfer coefficient K using formula (13) c F c The condensing temperature is calculated by formula (14). The regressed and fitted coefficients calculated are shown in Table 2 below. The evaporating temperature (unit: K) and the condensing temperature (unit: K) calculated according to the model are shown in Figure 11 .

[0183] Table 2: Fitting coefficient calculation results of the condenser heat transfer model

[0184]

[0185] 4. Establish the DCOP performance model of the water chiller.

[0186] The evaporating temperature and the condensing temperature of the chiller are calculated by formula (9) and formula (14), and the ideal COP value of the chiller is calculated by formula (15), which is defined as the ICOP value. The DCOP value is calculated by formula (16), which is the degree to which the actual COP value of the chiller approaches the ideal COP value, and is called the chiller performance coefficient. Finally, taking the load rate PLR as the abscissa and the chiller performance coefficient DCOP as the ordinate, and arranging the corresponding data points in the coordinate system, a dense scatter plot is formed. Then, the model coefficients are identified by regressing and fitting formula (17), and the DCOP performance model of the chiller is obtained. The regressed and fitted coefficients calculated and the corresponding model evaluation indexes are shown in Table 3 below.

[0187] Table 3: Fitting coefficient calculation results of the DCOP performance model

[0188]

[0189] The newly added chiller unit operation data is input into the trained DCOP performance model to calculate the DCOP prediction results and the change graph of the DCOP measured calculation results and the relative error change graph are shown in Figure 12 (a), (b) in Table 4.

[0190] Table 4 DCOP performance model error evaluation index of newly added data

[0191]

[0192] From Figure 12 (a), (b) and (c), it can be seen that for the input data without model training, the prediction results of the DCOP performance model are still relatively close to the measured results, and the generalization ability of the DCOP performance model is good.

[0193] 5. The DCOP performance prediction model of the chiller unit is established by the BP neural network model.

[0194] The BP neural network structure is established, which has three layers, as shown in Figure 13 The input neurons of the neural network are: chiller operating load rate PLR, condensing temperature and evaporating temperature difference T c -T e The number of network nodes in the hidden layer is 7; the output neuron is DCOP. The trainlm learning algorithm is used for the BP neural network model, the tansig function is selected for the network hidden layer transfer function, the Pureline function is selected for the output layer, the learning rate of the BP neural network model is set to 0.05, the maximum learning step is set to 1000 times, and the training target error is set to 0.003. The chiller DCOP prediction model is obtained through data training.

[0195] The training data error evaluation index of the DCOP prediction results and the DCOP measured calculation results is shown in Table 5. The newly added chiller unit operation data is input into the trained DCOP prediction model to calculate the DCOP prediction results and the change graph of the DCOP measured calculation results and the relative error change graph are shown in Figure 14 (a), (b), and the model error evaluation index is shown in Table 6. It can be seen that the DCOP performance prediction model established by the neural network has high accuracy, but from Figure 14 (a), (b), (c), when the newly added input data deviates from the training data of the model, the error decreases, indicating that the generalization ability of the model is poor.

[0196] Table 5 DCOP prediction model training data error evaluation index

[0197]

[0198] Table 6. New Data Error Evaluation Indicators for DCOP Prediction Model

[0199]

[0200] 6. The chiller unit model was established by integrating the DCOP performance model and COP performance prediction model of the chiller unit based on the K-means clustering algorithm.

[0201] 1) Cluster center calculation: The input data of the DCOP prediction model is clustered using the K-means clustering method. The optimal number of cluster centers k is found in the interval [2,10] using the elbow method, resulting in cluster centers p1, p2, ..., p1. k In this embodiment, the number of cluster centers k is calculated using the elbow method, with a value of 5. The Euclidean distances d1, d2, ..., d from the input parameters to the cluster centers are calculated using formula (18). k The coordinates of cluster centers p1, p2, p3, p4, p5, p6, and p7 are shown in Table 7.

[0202] Table 7 Cluster center calculation results

[0203]

[0204] 2) Calculate the cluster center proximity I using the new data.

[0205] 3) Using I' (preset similarity) as the boundary, when the similarity is higher than I', it indicates that the current data group is close to the input neurons in the BP neural network, so the air conditioning system DCOP performance prediction model established by the BP neural network is selected; when the similarity is less than or equal to I', it indicates that the air conditioning system DCOP performance model established by parameter identification has higher prediction accuracy, so the air conditioning system DCOP performance model established by parameter identification is selected. In this embodiment, I' is set to 0.8. The newly added data error evaluation index is shown in Table 8.

[0206] Table 8. Evaluation Indicators for Newly Added Data in the Chiller Unit Model

[0207]

[0208] 4) Construct a performance model for the chiller.

[0209] The COP of the chiller unit was calculated using formula (20). A comparison chart of the measured COP and the model-predicted COP of the chiller unit, along with the change in relative error, is shown below. Figure 15 The newly added data error evaluation indicators (a), (b), and (c) are shown in Table 9. It can be seen that the final chiller unit model has high prediction accuracy, and its generalization and adaptive capabilities are also good.

[0210] Table 9 COP prediction error evaluation index of water chiller model C

[0211]

[0212] It can be seen from the above examples that, in the control method provided by the embodiments of the present application, the actual energy efficiency ratio of the water chiller under different weather conditions and different cooling load rates, the ideal energy efficiency ratio under multiple conditions, and the target heat transfer coefficient of the evaporator and the target heat transfer coefficient of the condenser can be quantitatively characterized in a curve manner. Based on the physical framework of the water chiller, an actual performance model of the water chiller is established by using actual data, then a performance prediction model of the water chiller is established by using a BP neural network, and finally the high-precision prediction interval of the actual performance model of the water chiller and the performance prediction model is combined by using a K-means clustering method to obtain a target performance model of the water chiller. The target performance model obtained by the scheme is completely based on actual data, and thus can well reflect the actual performance of the water chiller under different load rates, greatly improves the prediction accuracy of the water chiller model, and solves the problems that the traditional water chiller performance curve cannot be applied to actual projects, the prediction accuracy of the existing water chiller performance model is not high, and the self-adaptation ability and universality are poor. According to the target performance model, a target energy efficiency ratio can also be obtained, and thus a more reasonable and more accurate refrigerating capacity can be determined according to the target energy efficiency ratio, which can effectively reduce the energy consumption of the water chiller in operation.

[0213] It can be seen that the above mainly introduces the scheme provided by the embodiments of the present application from the perspective of method. In order to implement the above functions, the embodiments of the present application provide corresponding hardware structures and / or software modules for executing various functions. Those skilled in the art should easily realize that, in combination with the modules and algorithm steps of the examples described in the embodiments disclosed in the present text, the embodiments of the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical scheme. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0214] The embodiments of the present application can divide the functions of the controller according to the above method examples, for example, each function module can be divided according to each function, or two or more functions can be integrated in one processing module. The above integrated module can be realized in the form of hardware or in the form of a software function module. Optionally, the division of the modules in the embodiments of the present application is illustrative, and is only a logical function division. When actually implemented, there can be another division method.

[0215] This application also provides a hardware structure diagram of a controller, such as... Figure 16 As shown, the controller 104 includes a processor 107, and optionally, a memory 108 and a communication interface 109 connected to the processor 107. The processor 107, memory 108, and communication interface 109 are connected via a bus 110.

[0216] Processor 107 may be a central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. Processor 107 may also be any other device with processing capabilities, such as a circuit, device, or software module. Processor 107 may also include multiple CPUs, and processor 107 may be a single-core processor or a multi-core processor. Here, "processor" may refer to one or more devices, circuits, or processing cores used to process data (e.g., computer program instructions).

[0217] The memory 108 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or it may be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer. This application embodiment does not impose any limitations on this. The memory 108 may exist independently or may be integrated with the processor 107. The memory 108 may contain computer program code. The processor 107 is used to execute the computer program code stored in the memory 108, thereby implementing the control method provided in this application embodiment.

[0218] The communication interface 109 can be used to communicate with other devices or communication networks (e.g., Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.). The communication interface 109 can be a module, a circuit, a transceiver, or any device capable of enabling communication.

[0219] The bus 110 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 110 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 16 Only one thick line is used in the figure to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0220] The embodiment of the present application further provides a computer readable storage medium, including computer execution instructions, when the computer execution instructions run on the computer, causing the computer to execute any one of the control methods provided by the above-mentioned embodiments.

[0221] The embodiment of the present application further provides a computer program product including computer execution instructions, when the computer execution instructions run on the computer, causing the computer to execute any one of the control methods provided by the above-mentioned embodiments.

[0222] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer-executable instructions. When the computer-executable instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer-executable instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer-executable instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or include one or more data storage devices such as servers, data centers, etc. that can be integrated with the medium. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0223] Although the present application is described herein in conjunction with various embodiments, it is understood that other variations of the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from an inspection of the drawings, the disclosure, and the appended claims. The word "comprising" does not exclude other components or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. A single processor or other unit can fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to an advantage.

[0224] Although the present application is described herein in conjunction with various embodiments, it is understood that other variations of the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from an inspection of the drawings, the disclosure, and the appended claims. The word "comprising" does not exclude other components or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. A single processor or other unit can fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to an advantage.

[0225] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any change or replacement within the technical scope disclosed by the present application should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An air conditioning system, characterized by, The system comprises: an evaporator for converting refrigerant from a normal temperature liquid state to a low temperature gaseous state to achieve refrigeration purposes; a condenser for converting refrigerant from a high temperature gaseous state to a normal temperature liquid state to achieve heating purposes; a controller electrically connected to the evaporator and the condenser, the controller being configured to: obtain the evaporating temperature, the condensing temperature, the first energy efficiency ratio and the load rate of the air conditioning system according to the operation data of the evaporator and the condenser within a preset time period; the operation data of the evaporator and the condenser within the preset time period includes the chilled water supply temperature, the chilled water return temperature, the chilled water flow and the evaporator evaporating temperature of the evaporator, the cooling water supply temperature, the cooling water return temperature, the cooling water flow and the condenser condensing temperature of the condenser, the chiller load rate and the chiller power of the air conditioning system; wherein the operation data corresponding to each time point within the preset time period constitutes a data group; obtain the second energy efficiency ratio of the air conditioning system and the first corresponding relationship between the second energy efficiency ratio and the load rate of the air conditioning system according to the evaporating temperature, the condensing temperature, the first energy efficiency ratio and the load rate; obtain the second corresponding relationship between the second energy efficiency ratio and the load rate of the air conditioning system by using a back propagation neural network model; obtain the third corresponding relationship between the target energy efficiency ratio of the air conditioning system and the load rate of the air conditioning system based on the mean value clustering algorithm using the first corresponding relationship and the second corresponding relationship; obtain the third corresponding relationship between the target energy efficiency ratio of the air conditioning system and the load rate of the air conditioning system based on the mean value clustering algorithm using the first corresponding relationship and the second corresponding relationship, comprising: obtain the data similarity of the current data group and the target data group in the operation data based on the chiller load rate, the temperature difference between the evaporating temperature and the condensing temperature of the air conditioning system; the current data group includes operation data obtained after the preset time period; in the case where the data similarity is less than or equal to a preset similarity, establish the third corresponding relationship according to the first corresponding relationship; in the case where the data similarity is greater than the preset similarity, establish the third corresponding relationship according to the second corresponding relationship.

2. The air conditioning system of claim 1, wherein, the controller is configured to obtain the evaporating temperature of the air conditioning system, comprising: obtain the chiller direct load according to the specific heat capacity of water and the chilled water flow, the chilled water return temperature and the chilled water supply temperature in the target data group in the operation data; obtain the chiller cooling capacity according to the specific heat capacity of water and the cooling water flow, the cooling water return temperature and the cooling water supply temperature in the target data group in the operation data; obtain the evaporator logarithmic mean temperature difference corresponding to the target data group according to the temperature difference between the chilled water supply temperature and the evaporator evaporating temperature in the target data group and the temperature difference between the chilled water return temperature and the evaporator evaporating temperature in the target data group; obtain the evaporator heat transfer coefficient corresponding to the target data group according to the chiller direct load and the evaporator logarithmic mean temperature difference; According to the evaporator heat transfer coefficients corresponding to different data groups, an evaporator target heat transfer coefficient is fitted and obtained; According to the water density, the water specific heat capacity, the evaporator target heat transfer coefficient, the cold machine direct load, the chilled water flow and the chilled water supply temperature, an evaporating temperature of the air conditioning system is obtained.

3. The air conditioning system of claim 1, wherein, The controller is configured to obtain a condensing temperature of the air conditioning system, including: According to the water specific heat capacity and the chilled water flow, the chilled water return temperature and the chilled water supply temperature in the target data group in the operation data, a cold machine direct load is obtained; According to the water specific heat capacity and the chilled water flow, the chilled water return temperature and the chilled water supply temperature in the target data group in the operation data, a cold machine direct load is obtained; According to the chilled water supply temperature and the condenser condensing temperature in the target data group, and the chilled water return temperature and the condenser condensing temperature in the target data group, a condenser logarithmic mean temperature difference corresponding to the target data group is obtained; According to the cold machine direct load and the condenser logarithmic mean temperature difference, a condenser heat transfer coefficient corresponding to the target data group is obtained; According to the condenser heat transfer coefficients corresponding to different data groups, a condenser target heat transfer coefficient is fitted and obtained; According to the water density, the water specific heat capacity, the condenser target heat transfer coefficient, the cold machine direct load, the chilled water flow and the chilled water return temperature, a condensing temperature of the air conditioning system is obtained.

4. The air conditioning system of any of claims 2-3, wherein, The controller is further configured: According to the cold machine direct load and the cold machine cooling capacity, and the cold machine power in the target data group in the operation data, a load imbalance rate is obtained; In the case where the load imbalance rate is greater than or equal to a preset imbalance rate, the data in the target data group in the operation data is deleted.

5. The air conditioning system of any of claims 2-3, wherein, The controller is further configured: According to the cold machine direct load and the cold machine power in the target data group in the operation data, a first energy efficiency ratio of the air conditioning system is obtained; In the case where the first energy efficiency ratio is outside a preset interval, the data in the target data group in the operation data is deleted.

6. The air conditioning system of claim 1, wherein, The controller is configured to obtain a second energy efficiency ratio of the air conditioning system and a first correspondence relationship between the second energy efficiency ratio and the load rate of the air conditioning system according to the evaporating temperature, the condensing temperature, the first energy efficiency ratio and the load rate, including: According to the evaporating temperature, the condensing temperature, the first energy efficiency ratio and the load rate, a second energy efficiency ratio of the air conditioning system is obtained; A scatter plot composed of a plurality of data points is generated by taking the second energy efficiency ratio as the abscissa and the load rate corresponding to the second energy efficiency ratio as the ordinate; wherein each data point corresponds to a second energy efficiency ratio and a load rate; The data points on the scatter plot are fitted to obtain the first correspondence relationship represented by a curve.

7. The air conditioning system of claim 1, wherein, The controller is configured to obtain a second correspondence relationship between the second energy efficiency ratio and the load rate of the air conditioning system by using a back propagation neural network model, including: The cold machine load rate in the operation data and the temperature difference between the evaporation temperature and the condensation temperature of the air conditioning system are input into the back propagation neural network model to obtain a second energy efficiency ratio and a second corresponding relationship between the second energy efficiency ratio and the load rate of the air conditioning system.

8. A control method of an air conditioning system, characterized by, The method comprises: According to the operation data of the evaporator and the condenser within a preset time length, the evaporation temperature, the condensation temperature, the first energy efficiency ratio and the load rate of the air conditioning system are obtained. The operation data of the evaporator and the condenser within the preset time length includes the chilled water supply temperature, the chilled water return temperature, the chilled water flow and the evaporator evaporation temperature of the evaporator, the cooling water supply temperature, the cooling water return temperature, the cooling water flow and the condenser condensation temperature of the condenser, the cold machine load rate and the cold machine power of the air conditioning system. Each time point corresponding to the operation data within the preset time length constitutes a data group; According to the evaporation temperature, the condensation temperature, the first energy efficiency ratio and the load rate, the second energy efficiency ratio of the air conditioning system and the first corresponding relationship between the second energy efficiency ratio and the load rate of the air conditioning system are obtained; The second corresponding relationship between the second energy efficiency ratio and the load rate of the air conditioning system is obtained by using a back propagation neural network model; Based on the mean value clustering algorithm, the first corresponding relationship and the second corresponding relationship are used to obtain the third corresponding relationship between the target energy efficiency ratio of the air conditioning system and the load rate of the air conditioning system; The third corresponding relationship between the target energy efficiency ratio of the air conditioning system and the load rate of the air conditioning system is obtained based on the mean value clustering algorithm using the first corresponding relationship and the second corresponding relationship, comprising: Based on the cold machine load rate, the temperature difference between the evaporation temperature and the condensation temperature of the air conditioning system, the data similarity between the current data group and the target data group in the operation data is obtained; The current data group includes operation data obtained after the preset time length; In the case where the data similarity is less than or equal to a preset similarity, the third corresponding relationship is established according to the first corresponding relationship; In the case where the data similarity is greater than the preset similarity, the third corresponding relationship is established according to the second corresponding relationship.

Images