Method for controlling energy efficiency of refrigerating machine room of subway station

Abstract

The invention provides a subway station refrigerating machine room energy efficiency control method which is characterized by comprising the steps that a historical data set is acquired, and the historical data set comprises the refrigerating machine room energy efficiency ratio and operation parameters; performing data standardization on the historical data set to generate a standardized historical data set; performing clustering analysis on the standardized historical data set and generating a plurality of clusters; performing correlation analysis and sensitivity analysis on the energy efficiency ratios of the refrigerating machine rooms in the plurality of clusters and the operating parameters, and obtaining a key variable priority sequence of the operating parameters on the energy efficiency ratios of the refrigerating machine rooms; and the key variable priority sequence is used for subway station refrigerating machine room energy efficiency control.

Description

Technical Field

[0001] The present application relates to the field of rail transportation, and specifically to a method for controlling the energy efficiency of a refrigeration room in a subway station. Background Art

[0002] Rail transit has gradually become the backbone of public transportation in large cities. As of the end of 2021, my country's urban rail transit system had a total of 5,216 stations in operation. According to statistics, over 30% of a subway station's energy consumption comes from the air conditioning system, and the energy efficiency of the air conditioning system directly determines the overall energy efficiency of the subway station.

[0003] Parameter adjustment and diagnosis of railway station refrigeration rooms are crucial for reducing building energy consumption, conserving energy, maintaining good indoor comfort, and improving indoor air quality. Prior art typically requires establishing a model and then using it for parameter adjustment, fault detection, and diagnosis. For example, Chinese patent CN112084707A discloses a refrigeration room energy-saving optimization method and system based on decoupling the variable flow rates of chilled and cooling water. This method improves the existing MP model of a chiller unit by applying a GRNN-based cooling water inlet temperature modeling method. Through device modeling, system simulation, orthogonal testing, and regression analysis, an orthogonal testing method suitable for decoupling the variable flow rates of chilled and cooling water in the refrigeration room is used to determine the chilled water flow rate, cooling water flow rate, chilled water supply temperature, and cooling water inlet temperature parameters that minimize the total energy consumption of the refrigeration room under these conditions. The energy consumption of each device and system before and after optimization is compared, and the devices are adjusted accordingly.

[0004] However, model development and validation require significant investment. Furthermore, a single model has limited versatility and can only be used within certain systems, making it difficult to promote. Summary of the Invention

[0005] To solve the above problems, the purpose of this application is to provide a method for quickly determining parameters that affect the energy efficiency of a subway station refrigeration room, thereby enabling the diagnosis of subway refrigeration system failures and system optimization.

[0006] The present application provides a method for controlling the energy efficiency of a subway station refrigeration room, including:

[0007] S1) obtaining a historical data set, wherein the historical data set includes an energy efficiency ratio and operating parameters of a refrigeration room;

[0008] S2) performing data standardization on the historical data set to generate a standardized historical data set;

[0009] S3) performing cluster analysis on the standardized historical data set and generating a plurality of clusters;

[0010] S4) performing correlation analysis and sensitivity analysis on the energy efficiency ratios of the refrigeration rooms in the multiple clusters and the operating parameters and obtaining a priority ranking of key variables of the operating parameters on the energy efficiency ratios of the refrigeration rooms;

[0011] S5) Prioritizing the key variables for energy efficiency control of subway station refrigeration rooms.

[0012] Furthermore, in the method for controlling the energy efficiency of the subway station refrigeration room, the operating parameters include the condenser cooling water inlet temperature, the evaporator chilled water outlet temperature, the condenser cooling water inlet and outlet temperature difference, the evaporator chilled water supply and return water temperature difference, the outdoor dry-bulb temperature, the outdoor wet-bulb temperature, the refrigeration unit power, the chilled water pump power, the cooling water pump power and the cooling tower power and the cooling capacity of the room.

[0013] Furthermore, the method for controlling the energy efficiency of the subway station refrigeration room adopts Z-score standardization to perform data standardization on the historical data set.

[0014] Furthermore, the method for controlling the energy efficiency of the subway station refrigeration room adopts a K-means clustering algorithm to perform cluster analysis on the standardized historical data set.

[0015] Furthermore, in the method for controlling energy efficiency of a subway station refrigeration room, the number of the multiple clusters is 4.

[0016] Furthermore, in the method for controlling the energy efficiency of the subway station refrigeration room, the correlation analysis adopts the Pearson coefficient method.

[0017] Furthermore, in the method for controlling the energy efficiency of the subway station refrigeration room, the sensitivity analysis adopts a sensitivity coefficient method.

[0018] Furthermore, the control method of the energy efficiency of the subway station refrigeration room adopts the calculation expression of the sensitivity coefficient method as follows:

[0019]

[0020] Where |O-Om| is the higher value of |Omax-Om| or |Omin-Om|;

[0021] Omax is the maximum value of the energy efficiency ratio of the refrigeration room in the multiple clusters;

[0022] Omin is the minimum value of the energy efficiency ratio of the refrigeration room in the multiple clusters;

[0023] Om is the average value of the energy efficiency ratio of the refrigeration room in the multiple clusters;

[0024] |I-Im| is the higher value of |Imax-Im| or |Imin-Im|;

[0025] Imax is the maximum value of the operating parameter in the multiple clusters;

[0026] Imin is the minimum value of the operating parameter in the multiple clusters;

[0027] Im is the average value of the operating parameters in the multiple clusters;

[0028] SC is the sensitivity coefficient.

[0029] The present application also provides a device for controlling the energy efficiency of a refrigeration room in a subway station, comprising a memory and a processor;

[0030] The memory is used to store computer programs;

[0031] The processor is configured to implement the above-mentioned method for controlling the energy efficiency of the subway station refrigeration room when executing the computer program.

[0032] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the above-mentioned method for controlling the energy efficiency of a subway station refrigeration room is implemented.

[0033] The technical solution provided by the embodiments of the present application has the following advantages:

[0034] 1. Using cluster analysis to process data, similar cases are classified and the cluster center is determined by iteratively analyzing the distance between samples and the cluster center. This is a simple and easy clustering method suitable for large-scale data processing.

[0035] 2. Through correlation analysis and sensitivity analysis of operating parameters, this method can be completed without relying on model analysis, reducing the amount of calculation and facilitating promotion, making it suitable for the diagnosis and optimization of energy efficiency deviation faults in different subway stations;

[0036] 3. Prioritize the key variables obtained, which can be used to optimize the energy consumption of the entire system, thereby achieving the most efficient operation of the refrigeration room system. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flow chart of a method for controlling energy efficiency of a subway station refrigeration room, which is preferred in an embodiment of the present invention;

[0038] Figure 2 A flow chart of a cluster analysis method for controlling the energy efficiency of a subway station refrigeration room, which is preferred in an embodiment of the present invention;

[0039] Figure 3 A flowchart of a correlation analysis method for a method for controlling energy efficiency of a subway station refrigeration room, which is preferred in an embodiment of the present invention;

[0040] Figure 4 This is a schematic diagram of cluster K index evaluation results of a specific application example of the method for controlling the energy efficiency of a subway station refrigeration room preferred in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the implementation of this application clearer, the technical solutions in the embodiments of this application will be described in more detail below in conjunction with the drawings in the embodiments of this application. In the drawings, the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions. The described embodiments are part of the embodiments of this application, not all of the embodiments. The embodiments described below with reference to the drawings are exemplary and are intended to be used to explain this application, and should not be understood as limitations on this application. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0042] In addition, it should be noted that, unless otherwise clearly stipulated and limited, the words "install", "connect", "connect" and similar terms used in the description of this application should be understood in a broad sense. For example, the connection can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, an indirect connection through an intermediate medium, or a connection between two components. Technical personnel in the field can understand their specific meanings in this application according to the specific circumstances.

[0043] Figure 1 This is a flow chart of a method for controlling the energy efficiency of a subway station refrigeration room, which is preferred in an embodiment of the present invention. Figure 1 As shown, a method for controlling the energy efficiency of a subway station refrigeration room includes:

[0044] S1) obtaining a historical data set, wherein the historical data set includes an energy efficiency ratio and operating parameters of a refrigeration room;

[0045] S2) performing data standardization on the historical data set to generate a standardized historical data set;

[0046] S3) performing cluster analysis on the standardized historical data set and generating a plurality of clusters;

[0047] S4) performing correlation analysis and sensitivity analysis on the energy efficiency ratios of the refrigeration rooms in the multiple clusters and the operating parameters and obtaining a priority ranking of key variables of the operating parameters on the energy efficiency ratios of the refrigeration rooms;

[0048] S5) Prioritizing the key variables for energy efficiency control of subway station refrigeration rooms.

[0049] The specific steps are further explained below.

[0050] Step 1) Obtain a historical data set, wherein the historical data set includes the energy efficiency ratio and operating parameters of the refrigeration room.

[0051] Specifically, operating parameters include the condenser cooling water inlet temperature, evaporator chilled water outlet temperature, condenser cooling water inlet and outlet temperature difference, evaporator chilled water supply and return temperature difference, outdoor dry-bulb temperature, outdoor wet-bulb temperature, refrigeration unit power, chilled water pump power, cooling water pump power, cooling tower power, and the cooling capacity of the computer room. Based on the selected parameters and changes in environmental parameters, the operating system with the corresponding parameters is selected and recorded. The energy efficiency ratio (EER) of the refrigeration room is calculated from the operating parameters. The calculation expression for the energy efficiency ratio (EER) of the refrigeration room is:

[0052]

[0053] E total =E ch +E cwp +E chwp +E ctf ;

[0054] Among them, Q c is the cooling capacity of the computer room, E total is the overall energy consumption of the refrigeration room;

[0055] E ch is the power of the refrigeration unit;

[0056] E cwp is the chilled water pump power;

[0057] E chwp is the cooling water pump power;

[0058] E ctf is the cooling tower power.

[0059] Step 2) performing data standardization on the historical data set to generate a standardized historical data set.

[0060] In this embodiment, the historical data set is preferably normalized using Z-score normalization. Z-score normalization is a commonly used data normalization method used to convert data into a form with a standard normal distribution. This method is achieved by calculating the difference between each data point and the mean of the data set and dividing it by the standard deviation of the data set. This can convert the data into a distribution with a mean of 0 and a standard deviation of 1, making the data comparable at different scales. Specifically, the mean of the indicator needs to be calculated first. and standard deviation (SD), and then use each observation of the variable Subtract the mean Divide it by the standard deviation (SD), which is:

[0061]

[0062] After Z-score standardization, the data will conform to the standard normal distribution, that is, about half of the observations will have values ​​less than 0, and the other half will have values ​​greater than 0. The mean of the variable is 0, the standard deviation is 1, and the range of variation is -1≤x′≤1.

[0063] Step 3) performing cluster analysis on the standardized historical data set and generating multiple clusters.

[0064] In this embodiment, the standardized historical data set is preferably clustered using a K-means clustering algorithm, and the number of the plurality of clusters is 4, that is, the optimal value of cluster k is calculated to be 4.

[0065] Figure 2 This is a flow chart of the cluster analysis method for the control method of the energy efficiency of the subway station refrigeration room preferred in the embodiment of the present invention. Figure 2 As shown, the number of clusters is obtained and the cluster center K is initialized. The standardized historical data set is assigned to each data object in the closest class, and then the center of each class is recalculated until convergence and the result is output.

[0066] In this embodiment, the evalclusters function is preferably used to determine the optimal number of clusters k. The code is as follows:

[0067] eva=evalclusters(X,'kmeans','CalinskiHarabasz','KList',2:20)

[0068] eva=evalclusters(X,'kmeans','SilhouetteCoefficient','KList',2:20)

[0069] eva=evalclusters(X,'kmeans','DaviesBoulding','KList',2:20)

[0070] Among them, the larger the CH and SC values ​​are and the smaller the DB index is, the better the corresponding number of clusters is, and the better the compactness, separation and stability of the final clustering results are.

[0071] In this embodiment, SPSS software is preferably used to cluster a large amount of operating data of the refrigeration system. The clustering principle and calculation expression are roughly as follows. The K-means algorithm first randomly selects k objects, each of which represents the centroid of a cluster. For each of the remaining objects, it is assigned to the cluster that is most similar to it based on the distance between the object and the centroid of each cluster. Then, the new centroid of each cluster is calculated. The above process is repeated until the criterion function converges. The criterion function commonly used is the squared-error criterion function, and the calculation expression is:

[0072]

[0073] Where E is the sum of squared errors of all objects in a data set, P is an object, and mi is the centroid of the cluster ci, that is:

[0074]

[0075] Step 4) performing correlation analysis and sensitivity analysis on the energy efficiency ratio of the refrigeration room in the multiple clusters and the operating parameters and obtaining a priority ranking of key variables of the operating parameters on the energy efficiency ratio of the refrigeration room.

[0076] Figure 3 This is a flow chart of the correlation analysis method for the preferred method of controlling the energy efficiency of the subway station refrigeration room according to the embodiment of the present invention. Figure 3 As shown, correlation is determined for multiple collected data (clusters) to determine the linear correlation coefficient r. Preferably, in this embodiment, the Pearson coefficient method is used on multiple clusters generated by the K-means algorithm to analyze the correlation between the energy efficiency ratio (EER) of the refrigeration room and various variables of the operating parameters between different clusters.

[0077] A positive correlation means that a larger value of variable X (variables of operating parameters between different clusters) is associated with a larger value of variable Y (EER of the cooling room), while a negative correlation means that a larger value of X is associated with a smaller value of Y, and vice versa. In this embodiment, preferably, variables of operating parameters are selected for which the correlation with the Pearson correlation is within the 95% confidence interval. The preferred Pearson coefficient calculation formula in this embodiment is as follows:

[0078]

[0079] Where,

[0080] Specifically, the sensitivity analysis uses the sensitivity coefficient method. For each cluster with similar operating conditions, the minimum, maximum, and average values ​​of the energy efficiency ratio (EER) of the refrigeration room are calculated. Preferably, the calculation expression of the sensitivity coefficient method is:

[0081]

[0082] Where |O-Om| is the higher value of |Omax-Om| or |Omin-Om|;

[0083] Omax is the maximum value of the energy efficiency ratio of the refrigeration room in the multiple clusters;

[0084] Omin is the minimum value of the energy efficiency ratio of the refrigeration room in the multiple clusters;

[0085] Om is the average value of the energy efficiency ratio of the refrigeration room in the multiple clusters;

[0086] |I-Im| is the higher value of |Imax-Im| or |Imin-Im|;

[0087] Imax is the maximum value of the operating parameter in the multiple clusters;

[0088] Imin is the minimum value of the operating parameter in the multiple clusters;

[0089] Im is the average value of the operating parameters in the multiple clusters;

[0090] SC is the sensitivity coefficient.

[0091] According to the definition of SC, the higher the value of the operating variable SC, the greater the change in the energy efficiency ratio (EER) of the refrigeration room.

[0092] The present application also discloses a device for controlling the energy efficiency of a refrigeration room in a subway station, comprising a memory and a processor;

[0093] The memory is used to store computer programs;

[0094] The processor is configured to implement the above-mentioned method for controlling the energy efficiency of the subway station refrigeration room when executing the computer program.

[0095] The present application also discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned method for controlling the energy efficiency of a subway station refrigeration room is implemented.

[0096] Example

[0097] This example collects actual operating data from the automatic control system monitoring of a subway station in Shanghai. The cooling source of the air-conditioning system uses two magnetic levitation chillers, each with a cooling capacity of 528kW; the freezing side is equipped with two chilled water pumps, each with a flow rate of 100m 3 / h; the cooling side is equipped with two cooling water pumps with a flow rate of 100m 3 / h, and configure 300m 3 / h flow cooling tower. In this embodiment, the system continuously detects and records data every 5 minutes, and a total of approximately 25,982 sets of operating data are collected and used for cluster analysis. The collected parameters are shown in Table 1 below:

[0098] Table 1 Operation variable collection parameters

[0099]

[0100]

[0101] SPSS software is used to cluster the selected operating data of the refrigeration system. SPSS contains analysis tools for three types of cluster analysis, namely hierarchical clustering, k-means clustering, and two-step clustering. In this embodiment, k-means clustering analysis is preferably used.

[0102] In order to ensure the reliability of the results, the selected operating data should first be standardized and converted into dimensionless and magnitude-free standardized values ​​to make the results more reliable and facilitate cluster analysis.

[0103] In this embodiment, the data are preferably normalized using the Z-score normalization method in SPSS software, and cluster analysis is performed on the data after normalization.

[0104] The k-means clustering algorithm is an iterative clustering analysis algorithm that randomly selects k objects as initial cluster centers. It then calculates the distance between each object and each seed cluster center, assigning each object to the cluster center closest to it. Before using k-means clustering, it is necessary to calculate the optimal number of clusters, k.

[0105] In this embodiment, preferably, MATLAB is used to calculate the CH (Calinski Harabasz) index in the evalclusters function, and the code is as follows:

[0106] eva=evalclusters(X,'kmeans','CalinskiHarabasz','KList',2:20)

[0107] The larger the CH value is, the better the corresponding number of clusters is, and the better the compactness, separation and stability of the final clustering results are.

[0108] Figure 4 This is a schematic diagram of the cluster K index evaluation results of a specific application example of the preferred method for controlling the energy efficiency of a subway station refrigeration room according to an embodiment of the present invention. Figure 4 As shown, the optimal value of cluster k is 4 calculated by using MATLAB.

[0109] In this embodiment, the four clusters assigned using the built-in clustering algorithm of the software SPSS are shown in Table 2. The number of cases in category 1 is 839, accounting for 3.2%; the number of cases in category 2 is 6125, accounting for 23.6%; the number of cases in category 3 is 10949, accounting for 42.1%; and the number of cases in category 4 is 8069, accounting for 31.1%.

[0110] Table 2 Final cluster center results

[0111]

[0112]

[0113] Through data analysis, for example, using box plots, the operating conditions such as the energy efficiency ratio (EER) of the refrigeration room, the COP of the chiller, the chiller outlet water temperature, the chilled water pump temperature difference, the cooling tower outlet water temperature, the cooling water pump temperature difference, the outdoor dry-bulb temperature, and the outdoor wet-bulb temperature are displayed in each cluster. The range of different variables in the four clusters can be analyzed. The analysis shows that in each cluster, the range of each operating variable is significantly different, which indicates that each cluster represents a different operating strategy and operating condition of the air-conditioning system. It can be seen from each cluster that cluster 1 mainly involves the operating condition of high chiller outlet water temperature. At this time, the energy efficiency ratio (EER) of the refrigeration room and the COP of the chiller are significantly higher than those of clusters 2, 3, and 4. The analysis of other clusters and operating conditions is similar and will not be repeated. There are a lot of overlapping areas between clusters. This is because there is a certain coupling relationship between the variables in the same cluster. Table 3 below lists the ranges of the different variables studied in the four clusters. As shown in Table 3 below:

[0114] Table 3 Final cluster center result range

[0115] Cluster 1 Cluster 2 Cluster 3 Cluster 4 Energy efficiency ratio (EER) of the cooling room 5.2～6.9 4.2～5.4 3.9～5.2 4.4～5.6 Chiller outlet water temperature 8.3～20.4 7.3～12.3 6.1～10.2 6.2～12.6 Chilled water pump temperature difference 2.3～6.1 3.2～5.4 3.8～5.7 2.4～5.5 Cooling tower outlet water temperature 20.0～30.8 25～31.22 28.2～32.2 21.7～27.6 Cooling water pump temperature difference 1.7～7.0 3.6～6.3 4.2～6.1 2.6～6.5 Outdoor dry-bulb temperature 24.2～38.0 24.56～35.5 27.3～39.5 20.0～33.4 Outdoor wet-bulb temperature 18.2～29.5 22.5～29.1 25.6～29.9 18.7～25.0

[0116] Based on the four clusters identified by cluster analysis and the results of data analysis (box plot), the Pearson coefficient method was used to analyze the correlation between the energy efficiency ratio (EER) of the refrigeration room and the variables in different clusters. The analysis results are shown in Tables 4 to 7 below. A positive correlation means that a larger value of variable X is associated with a larger value of variable Y, while a negative correlation means that a larger value of X is associated with a smaller value of Y, and vice versa. "*" highlights the correlation between two variables and the Pearson correlation within the 95% confidence interval.

[0117] Table 4 Pearson coefficients between variables in cluster 1

[0118]

[0119] Table 5 Pearson coefficients between variables in cluster 2

[0120]

[0121]

[0122] Table 6 Pearson coefficients between variables in cluster 3

[0123]

[0124] Table 7 Pearson coefficients between variables in cluster 4

[0125]

[0126] Tables 4 to 7 show that different cluster data show that the degree of correlation between the energy efficiency ratio (EER) of the refrigeration room and various operating variables is different. Cluster 1 shows that the energy efficiency ratio (EER) of the refrigeration room is mainly related to the temperature difference of the chilled water pump, the cooling tower outlet water temperature, the outdoor wet-bulb temperature, and the outdoor dry-bulb temperature. The energy efficiency ratio (EER) of the refrigeration room in clusters 2 and 4 is mainly related to the temperature difference of the chilled water pump, the cooling tower outlet water temperature, and the outdoor wet-bulb temperature. The energy efficiency ratio (EER) of the refrigeration room in cluster 3 is mainly related to the temperature difference of the chilled water pump and the cooling tower outlet water temperature.

[0127] For all clusters, the analysis revealed a high correlation between the cooling tower outlet water temperature and the outdoor wet-bulb temperature. Further analysis may be needed to determine whether the control and operation of the cooling towers depend on the outdoor temperature and whether the existing cooling tower controls can achieve energy-efficient operation. Furthermore, the cooling room energy efficiency ratio (EER) showed a relatively high correlation with the chilled water pump temperature difference. Further analysis of the chilled water pump operation strategy may be necessary, as this affects the trade-off between chiller compressor power and pump power to minimize total room power. Overall, correlation analysis can reveal operational issues with the historical dataset (operating parameters) regarding energy efficiency control in subway station cooling rooms.

[0128] After performing a correlation analysis on the operating parameters, a sensitivity analysis was performed. This sensitivity analysis aims to identify the impact of changes in non-operating variables during refrigeration system operation on the energy efficiency ratio (EER) of the refrigeration room. A sensitivity analysis was performed on the data highlighted by "*" in Tables 4 to 7 after the correlation analysis. The silhouette coefficient (SC) was analyzed to prioritize the key variables for the energy efficiency ratio of the refrigeration room.

[0129] In this embodiment, sensitivity analysis revealed that cooling tower outlet water temperature is most sensitive to changes in the cooling room's energy efficiency ratio (EER). Using this parameter as an example, this demonstrates that optimization potential exists in the cooling tower outlet water temperature control logic within the preferred system of this embodiment. This optimization can reduce energy consumption in subway station cooling rooms. By analyzing the controllers and control logic corresponding to each key variable in the priority ranking, optimization is performed to reduce overall energy consumption in subway station cooling rooms.

[0130] The present invention uses a K-means cluster analysis data processing algorithm to classify similar cases and determine the cluster center by iteratively analyzing the distance from the sample to the cluster center. This is a simple, easy-to-use clustering method suitable for large-scale data processing. By obtaining fault characteristics for decision-making research, fault analysis, and diagnosis, this method does not require an analytical model and has a low computational load, making it suitable for diagnosing energy efficiency offset faults in subway stations. Correlation analysis and sensitivity analysis are performed on the clustering results to estimate the energy-saving potential of different variables and predict the optimal state point of the variables. Recommendations are also provided for which controllable variables should be corrected first to improve system performance, thereby achieving the most efficient operation of the refrigeration room system.

[0131] Those skilled in the art will appreciate that information, signals, and data may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips cited throughout the foregoing description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0132] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or a combination of the two. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Technicians can implement the described functionality in different ways for each specific application, but such implementation decisions should not be interpreted as resulting in a departure from the scope of this application.

[0133] The various illustrative logic modules and circuits described in conjunction with the embodiments disclosed herein may be implemented or executed using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

[0134] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read and write information from / to the storage medium. In an alternative, the storage medium may be integrated into the processor. The processor and storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and storage medium may reside in a user terminal as discrete components.

[0135] In one or more exemplary embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functions may be stored on or transmitted via a computer-readable medium as one or more instructions or codes. Computer-readable media include both computer storage media and communication media, including any media that facilitates the transfer of a computer program from one location to another. A storage medium may be any available medium that can be accessed by a computer. By way of example and not limitation, such computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Any connection is also properly referred to as a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwaves, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwaves are included in the definition of medium. As used herein, disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, where disks typically reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0136] The above embodiments are provided for persons familiar with the art to implement or use the present application. Personnel familiar with the art may make various modifications or changes to the above embodiments without departing from the application concept of the present application. Therefore, the scope of protection of the present application is not limited to the above embodiments, but should be the maximum scope of the innovative features mentioned in the claims.

Claims

1. A method for controlling the energy efficiency of a subway station refrigeration room, characterized in that: include: S1) obtaining a historical data set, wherein the historical data set includes an energy efficiency ratio and operating parameters of a refrigeration room; S2) performing data standardization on the historical data set to generate a standardized historical data set; S3) performing cluster analysis on the standardized historical data set and generating a plurality of clusters; S4) performing correlation analysis and sensitivity analysis on the energy efficiency ratios of the refrigeration rooms in the multiple clusters and the operating parameters and obtaining a priority ranking of key variables of the operating parameters on the energy efficiency ratios of the refrigeration rooms; S5) Prioritizing the key variables for energy efficiency control of subway station refrigeration rooms.

2. The method for controlling energy efficiency of a subway station refrigeration room according to claim 1, characterized in that: The operating parameters include the condenser cooling water inlet temperature, the evaporator chilled water outlet temperature, the condenser cooling water inlet and outlet temperature difference, the evaporator chilled water supply and return water temperature difference, the outdoor dry-bulb temperature, the outdoor wet-bulb temperature, the refrigeration unit power, the chilled water pump power, the cooling water pump power and the cooling tower power and the cooling capacity of the machine room.

3. The method for controlling energy efficiency of a subway station refrigeration room according to claim 1, characterized in that: Z-score standardization is used to standardize the historical data set.

4. The method for controlling energy efficiency of a subway station refrigeration room according to claim 1, characterized in that: The standardized historical data set is clustered and analyzed using the K-means clustering algorithm.

5. The method for controlling energy efficiency of a subway station refrigeration room according to claim 1, characterized in that: The number of the plurality of clusters is 4.

6. The method for controlling energy efficiency of a subway station refrigeration room according to claim 1, characterized in that: The correlation analysis was performed using the Pearson coefficient method.

7. The method for controlling energy efficiency of a subway station refrigeration room according to claim 1, characterized in that: The sensitivity analysis adopts the sensitivity coefficient method.

8. The method for controlling energy efficiency of a subway station refrigeration room according to claim 7, characterized in that: The calculation expression using the sensitivity coefficient method is: Where |O-Om| is the higher value of |Omax-Om| or |Omin-Om|; Omax is the maximum value of the energy efficiency ratio of the refrigeration room in the multiple clusters; Omin is the minimum value of the energy efficiency ratio of the refrigeration room in the multiple clusters; Om is the average value of the energy efficiency ratio of the refrigeration room in the multiple clusters; |I-Im| is the higher value of |Imax-Im| or |Imin-Im|; Imax is the maximum value of the operating parameter in the multiple clusters; Imin is the minimum value of the operating parameter in the multiple clusters; Im is the average value of the operating parameters in the multiple clusters; SC is the sensitivity coefficient.

9. A control device for energy efficiency of a subway station refrigeration room, characterized in that: including memory and processor; The memory is used to store computer programs; The processor is configured to implement the method for controlling the energy efficiency of a subway station refrigeration room as claimed in any one of claims 1 to 8 when executing the computer program.

10. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by the processor, the method for controlling the energy efficiency of the subway station refrigeration room according to any one of claims 1 to 8 is implemented.

Images