Energy-saving optimization control method and system for water chilling unit of central air conditioner

Abstract

The invention provides an energy-saving optimization control method and system for water chilling units of a central air conditioner, and the method comprises the steps: after a data collection module collects the data volume of at least one year, optimizing the working strategy of the water chilling units by adopting the following method: S11, drawing a load rate-operation energy efficiency curve of each water chilling unit, sequencing and marking are carried out; s12, a building load multi-step prediction model is established and trained to predict 24-hour hourly load of the next day of the building; s13, making a primary working strategy of the water chilling unit in each time period corresponding to the next day by referring to historical operation data of the water chilling unit; s14, making an optimization working strategy of the water chilling unit in each time period of the next day by taking the minimum total energy consumption of the started water chilling unit as an optimization target; and S15, respectively starting the corresponding water chilling units in each time period of the next day according to the optimized working strategy formulated in the S14. Energy-saving optimization control of the central air conditioning system is achieved, and the method has high engineering application value.

Description

Technical Field

[0001] The present invention relates to the field of energy conservation, and in particular to an energy conservation optimization control method and system for a central air-conditioning chiller. Background Art

[0002] In recent years, with the rapid development of urbanization, building energy consumption has increased significantly, and building energy conservation research has become an important direction of energy conservation research; among them, the operating energy consumption of the air-conditioning system is the highest, accounting for more than 60% of the total energy consumption of the building, and has become the main energy consumer in the operation of the building. As an important part of the central air-conditioning system, the chiller accounts for 30%-40% of the total energy consumption of the actual operation of the central air-conditioning system. The optimized operation of the chiller greatly affects the energy consumption of the entire central air-conditioning system. Therefore, the efficient and energy-saving operation of the chiller is crucial to central air conditioning. The overall operating energy efficiency of the chiller has a huge impact on the energy consumption of the building, and it is a powerful entry point for building energy conservation optimization.

[0003] Therefore, how to adjust the working strategy of the chiller to achieve overall energy-saving optimization of central air conditioning is an important topic in the field of energy conservation. Summary of the invention

[0004] The purpose of the present invention is to provide an energy-saving optimization control method and system for a central air-conditioning chiller to address the above-mentioned problems in the prior art, thereby reducing the total energy consumption of the chiller during operation and achieving energy-saving optimization of the central air-conditioner.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] An energy-saving optimization control method for a central air-conditioning chiller unit, comprising:

[0007] The data acquisition module collects and stores historical operation data of the chillers in the central air conditioner, outdoor meteorological data, and building work schedule; the outdoor meteorological data includes outdoor temperature and outdoor relative humidity; the historical operation data of the chillers includes the start time, shutdown time, maintenance records of each chiller, and load rate and operation energy efficiency during the working period;

[0008] After the data acquisition module has collected at least one year's worth of data, the following methods are used to optimize the chiller's operating strategy:

[0009] S11. Draw the load rate-operation energy efficiency curve of each chiller according to the historical operation data of the chiller, and sort and mark the operation energy efficiency of all chillers in different distribution ranges of the load rate;

[0010] S12. Based on the historical operation data of the chiller and the outdoor meteorological data, a multi-step prediction model for building load is established and trained to predict the 24-hour hourly load of the building the next day;

[0011] S13, dividing the 24 hours of a day into multiple time periods, referring to the number of chillers turned on in each time period in the historical operation data of the chillers and the rated cooling capacity of each chiller turned on, formulating the primary working strategy of the chillers in each time period corresponding to the next day; the primary working strategy refers to the number of chillers that should be turned on in each time period of the next day, and the rated cooling capacity that each chiller turned on needs to achieve;

[0012] S14, according to the primary working strategy determined in S13, the hourly load of the next day for 24 hours predicted in S12, and the ranking and marking results of the chiller operation efficiency obtained in S11, with the minimum total energy consumption of the chillers turned on as the optimization goal, formulate the optimal working strategy of the chillers in each time period of the next day; the optimal working strategy refers to which chillers should be turned on in each time period of the next day;

[0013] S15. According to the optimized working strategy formulated in S14, corresponding chillers are started in different time periods of the next day.

[0014] Furthermore, the S11 includes:

[0015] S111. For each chiller, based on the collected load rate PLR ​​and operating energy efficiency COP i , establish the following operation energy efficiency model and use the least squares method to solve the model parameters:

[0016] COP i =β0+β1PLR+β2PLR 2 ;

[0017] Where: β0, β1, β2 are model parameters;

[0018] S112. Draw the load rate-operation energy efficiency curve of each chiller according to the operation energy efficiency model of each chiller;

[0019] S113. According to the load rate-operating energy efficiency curve of each chiller, the load rate distribution interval of all chillers is obtained, and the load rate distribution interval is further divided into multiple mutually exclusive sub-intervals; in each sub-interval, the operating energy efficiency of all chillers is sorted and marked respectively.

[0020] Further, the S12 includes:

[0021] S121. Based on the LSTM prediction model, outdoor temperature, outdoor relative humidity and building work schedule are selected as feature variables, and the total load of the chillers turned on in the building is selected as the output result to establish a multi-step prediction model for building load; the multi-step prediction model for building load is trained using the collected historical operation data of the chillers and outdoor meteorological data;

[0022] S122. Use the trained multi-step building load prediction model to predict the 24-hour hourly load of the building on the next day.

[0023] Furthermore, the S14 specifically includes:

[0024] When only one chiller needs to be started in a certain time period of the next day, the load rate of the time period is calculated according to the prediction result of S12, and then the chiller with the highest energy efficiency under the load rate is selected as the start target according to the sorting and marking results of S11;

[0025] When n (n ≥ 2) chillers need to be started during a certain period of time the next day, the total load Q of the period is calculated based on the prediction result of S12. n Then, taking the minimum total energy consumption of n chillers as the optimization goal, the PSO algorithm is used to solve the load rate of each chiller when the total energy consumption of n chillers is minimized:

[0026] PLR=(PLR1,PLR2,…,PLR n );

[0027] Among them, the total energy consumption of n chillers is:

[0028]

[0029] Where PLR i is the load factor of the i-th chiller, COP i is the operating energy efficiency of the i-th chiller, Q i is the rated cooling capacity of the i-th chiller, i=1,2,…,n;

[0030] The optimization constraints of the PSO algorithm are:

[0031] 0 <PLR i <1(i=1,2,…,n);

[0032]

[0033] After determining the load rate of each chiller according to the optimization results of the PSO algorithm, further according to the sorting and marking results of S11, the chiller with the highest operating efficiency at each load rate is selected as the start-up target.

[0034] Furthermore, it also includes: when the data collection module has not yet collected a full year of data, a rotation work strategy is used to optimize the working strategy of the chiller; the rotation work strategy is: based on the operating time of each chiller during the maintenance cycle, the chiller with a shorter operating time is started first.

[0035] Furthermore, the rotation work strategy specifically includes:

[0036] S21. According to the collected historical operation data of the chillers, the cumulative operation time t of each chiller after the most recent maintenance is counted;

[0037] S22, sorting the chillers in order of the accumulated running time t from short to long;

[0038] S23, when it is necessary to start the chiller, according to the order of S22, the chiller with the shorter cumulative running time t is started first;

[0039] S24, after the chillers have been turned on for a period of time, re-ranking the accumulated running time t of each chiller, and when the chillers are turned on next time, the chillers with shorter accumulated running time t are selected according to the new ranking to be turned on;

[0040] S25. If a chiller is maintained, the accumulated running time t of the chiller is reset to zero and the chillers are rearranged.

[0041] An energy-saving optimization control system for a central air-conditioning chiller, used in the above method, comprising:

[0042] A data acquisition module is used to collect and store historical operation data of the chillers in the central air conditioner, outdoor meteorological data and building work schedule; the outdoor meteorological data includes outdoor temperature and outdoor relative humidity; the historical operation data of the chillers includes the start time, shutdown time, maintenance records of each chiller, and load rate and operation energy efficiency during the working period;

[0043] The chiller load distribution optimization module is used to provide an optimized working strategy for the chiller after the data collection module has collected at least one year's worth of data, based on various known data, so as to reduce the overall energy consumption of the chiller;

[0044] The chiller control module is used to control each chiller to be turned on or off in different time periods according to the optimization working strategy provided by the chiller load distribution optimization module, so as to distribute the total load to the turned-on chillers;

[0045] In the chiller load distribution optimization module, the method for formulating the optimization working strategy is as follows:

[0046] S11. Draw the load rate-operation energy efficiency curve of each chiller according to the historical operation data of the chiller, and sort and mark the operation energy efficiency of all chillers in different distribution ranges of the load rate;

[0047] S12. Based on the historical operation data of the chiller and the outdoor meteorological data, a multi-step prediction model for building load is established and trained to predict the 24-hour hourly load of the building the next day;

[0048] S13, dividing the 24 hours of a day into multiple time periods, referring to the number of chillers turned on in each time period in the historical operation data of the chillers and the rated cooling capacity of each chiller turned on, formulating the primary working strategy of the chillers in each time period corresponding to the next day; the primary working strategy refers to the number of chillers that should be turned on in each time period of the next day, and the rated cooling capacity that each chiller turned on needs to achieve;

[0049] S14. Based on the primary working strategy determined in S13, the hourly load of the next day for 24 hours predicted in S12, and the ranking and marking results of the chiller operating efficiency obtained in S11, the optimization goal is to minimize the total energy consumption of the chillers that are turned on, and formulate an optimized working strategy for the chillers in each time period of the next day; the optimized working strategy refers to which chillers should be turned on in each time period of the next day.

[0050] Furthermore, the data acquisition module includes: a chiller data acquisition device, an outdoor meteorological data acquisition device and an industrial computer;

[0051] The chiller data collection device is connected to each chiller and is used to collect the start time, shut down time, maintenance records, and load rate and operating energy efficiency of each chiller during operation;

[0052] The outdoor meteorological data collection device is arranged in an outdoor space and is used to collect outdoor temperature and outdoor relative humidity;

[0053] The industrial computer is connected to the chiller data acquisition device and the outdoor meteorological data acquisition device through a network, and is used to classify, summarize and store the data collected by the chiller data acquisition device and the outdoor meteorological data acquisition device.

[0054] Further, in the chiller load distribution optimization module, the S14 specifically includes:

[0055] When only one chiller needs to be started in a certain time period of the next day, the load rate of the time period is calculated according to the prediction result of S12, and then the chiller with the highest energy efficiency under the load rate is selected as the start target according to the sorting and marking results of S11;

[0056] When n (n ≥ 2) chillers need to be started during a certain period of time the next day, the total load Q of the period is calculated based on the prediction result of S12. n Then, taking the minimum total energy consumption of n chillers as the optimization goal, the PSO algorithm is used to solve the load rate of each chiller when the total energy consumption of n chillers is minimized:

[0057] PLR=(PLR1,PLR2,…,PLR n );

[0058] Among them, the total energy consumption of n chillers is:

[0059]

[0060] Where PLR i is the load factor of the i-th chiller, COP i is the operating energy efficiency of the i-th chiller, Q i is the rated cooling capacity of the i-th chiller, i=1,2,…,n;

[0061] The optimization constraints of the PSO algorithm are:

[0062] 0 <PLR i <1(i=1,2,…,n);

[0063]

[0064] After determining the load rate of each chiller according to the optimization results of the PSO algorithm, further according to the sorting and marking results of S11, the chiller with the highest operating efficiency at each load rate is selected as the start-up target.

[0065] Furthermore, the chiller control module is also used to optimize the chiller's working strategy by adopting a rotation working strategy when the data collection module has not collected a full year's worth of data;

[0066] The rotation work strategy specifically includes:

[0067] S21. According to the collected historical operation data of the chillers, the cumulative operation time t of each chiller after the most recent maintenance is counted;

[0068] S22, sorting the chillers in order of the accumulated running time t from short to long;

[0069] S23, when it is necessary to start the chiller, according to the order of S22, the chiller with the shorter cumulative running time t is started first;

[0070] S24, after the chillers have been turned on for a period of time, re-ranking the accumulated running time t of each chiller, and when the chillers are turned on next time, the chillers with shorter accumulated running time t are selected according to the new ranking to be turned on;

[0071] S25. If a chiller is maintained, the accumulated running time t of the chiller is reset to zero and the chillers are rearranged.

[0072] The present invention is based on the accumulated historical data, establishes an operating energy efficiency model for chillers, analyzes and plots the load rate and operating energy efficiency of each chiller, and obtains the operating energy efficiency curve of each chiller; then, a multi-step building load prediction model is established according to the change of the total load in the historical data to predict the hourly load of the building for 24 hours the next day; finally, the number of chillers turned on in different time periods of the next day and the rated cooling capacity of each chiller are determined with reference to the historical data of each time period, and which chillers should be turned on in different time periods of the next day are determined according to the operating energy efficiency curve of the chillers and the optimization result of the PSO algorithm, so as to distribute the total load to the turned-on chillers and reduce the overall energy consumption of the chillers.

[0073] The present invention fully correlates the collected historical operation data of the chiller with the outdoor meteorological data to predict the future (next day) load demand, and further combines the historical start-up rules and energy efficiency characteristics of the chiller to deeply optimize the start-up strategy of the chiller, which can save a lot of electricity resources and realize energy-saving optimization control of the central air-conditioning system, and has high engineering application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 It is a flow chart of the rotation working strategy of the chiller in the first embodiment of the present invention.

[0075] Figure 2 This is a flow chart of the optimization of the working strategy of the chiller in the first embodiment of the present invention. DETAILED DESCRIPTION

[0076] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0077] Embodiment 1

[0078] The embodiment of the present invention provides an energy-saving optimization control method for a central air-conditioning chiller, comprising:

[0079] The data acquisition module collects and stores historical operation data of the chillers in the central air conditioner, outdoor meteorological data, and the building work schedule (i.e., the opening hours of the building equipment, including working hours, holidays, etc.); the outdoor meteorological data includes outdoor temperature and outdoor relative humidity; the historical operation data of the chillers includes the opening time, closing time, maintenance records of each chiller, and the load rate and operating energy efficiency during the working period;

[0080] When the data collection module has not collected a full year's worth of data, a rotation work strategy is used to optimize the working strategy of the chiller; the rotation work strategy is: based on the operating time of each chiller during the maintenance cycle, the chiller with a shorter operating time is started first to maintain the mechanical wear balance of similar equipment.

[0081] like Figure 1 As shown, the rotation work strategy specifically includes:

[0082] S21. According to the collected historical operation data of the chillers, the cumulative operation time t of each chiller after the most recent maintenance is counted;

[0083] S22, sorting the chillers in order of the accumulated running time t from short to long;

[0084] S23, when it is necessary to start the chiller, according to the order of S22, the chiller with the shorter cumulative running time t is started first;

[0085] S24, after the chillers have been turned on for a period of time, re-ranking the accumulated running time t of each chiller, and when the chillers are turned on next time, the chillers with shorter accumulated running time t are selected according to the new ranking to be turned on;

[0086] S25. If a chiller is maintained, the accumulated running time t of the chiller is reset to zero and the chillers are rearranged.

[0087] On the one hand, the rotation working strategy can keep the mechanical wear and life of each chiller balanced, and on the other hand, it can also ensure that each chiller has sufficient working time, so that the data acquisition module can collect sufficient historical operation data from each chiller, providing sufficient data support for subsequent energy-saving optimization work.

[0088] like Figure 2 As shown, after the data acquisition module has collected at least one year's worth of data, the following method is used to optimize the chiller's operating strategy:

[0089] S11. Draw the load rate-operation energy efficiency curve of each chiller according to the historical operation data of the chiller, and sort and mark the operation energy efficiency of all chillers in different distribution ranges of the load rate;

[0090] S12. Based on the historical operation data of the chiller and the outdoor meteorological data, a multi-step prediction model for building load is established and trained to predict the 24-hour hourly load of the building the next day;

[0091] S13, dividing the 24 hours of a day into multiple time periods, referring to the number of chillers turned on in each time period in the historical operation data of the chillers and the rated cooling capacity of each chiller turned on, formulating the primary working strategy of the chillers in each time period corresponding to the next day; the primary working strategy refers to the number of chillers that should be turned on in each time period of the next day, and the rated cooling capacity that each chiller turned on needs to achieve;

[0092] S14, according to the primary working strategy determined in S13, the hourly load of the next day for 24 hours predicted in S12, and the ranking and marking results of the chiller operation efficiency obtained in S11, with the minimum total energy consumption of the chillers turned on as the optimization goal, formulate the optimal working strategy of the chillers in each time period of the next day; the optimal working strategy refers to which chillers should be turned on in each time period of the next day;

[0093] S15. According to the optimized working strategy formulated in S14, corresponding chillers are started in different time periods of the next day.

[0094] Specifically, the S11 includes:

[0095] S111. For each chiller, based on the collected load rate PLR ​​and operating energy efficiency COP i , establish the following operation energy efficiency model and use the least squares method to solve the model parameters:

[0096] COP i =β0+β1PLR+β2PLR 2 ;

[0097] Where: β0, β1, β2 are model parameters;

[0098] S112. Draw the load rate-operation energy efficiency curve of each chiller according to the operation energy efficiency model of each chiller;

[0099] S113. According to the load rate-operating energy efficiency curve of each chiller, the load rate distribution interval of all chillers is obtained, and the load rate distribution interval is further divided into multiple mutually exclusive sub-intervals; in each sub-interval, the operating energy efficiency of all chillers is sorted and marked respectively.

[0100] Further, the S12 includes:

[0101] S121. Based on the LSTM prediction model, outdoor temperature, outdoor relative humidity and building work schedule are selected as feature variables, and the total load of the chillers turned on in the building is selected as the output result to establish a multi-step prediction model for building load; the multi-step prediction model for building load is trained using the collected historical operation data of the chillers and outdoor meteorological data;

[0102] S122. Use the trained multi-step building load prediction model to predict the building's 24-hour hourly load for the next day (i.e., the total load for each hour in the 24 hours of the next day).

[0103] Further, in S13, the number of chillers turned on in a certain time period and the rated cooling capacity of each chiller turned on can be counted in each day of the historical data, and the data in the time period of each day can be averaged and rounded as the primary working strategy for the next day. The outdoor temperature and outdoor relative humidity of the next day can also be obtained through the weather forecast, and then a certain day or some days with matching outdoor meteorological data can be found from the historical data, and the primary working strategy for the next day can be determined in the same way with reference to the historical data with matching outdoor meteorological data. In addition, those skilled in the art can also formulate the primary working strategy for the next day by referring to the historical operating data of the chiller in other more different ways, which should all be included in the technical solution claimed for protection of the present invention and will not be described one by one here.

[0104] Furthermore, the S14 specifically includes:

[0105] When only one chiller needs to be started in a certain time period of the next day, the load rate of the time period is calculated according to the prediction result of S12, and then the chiller with the highest energy efficiency under the load rate is selected as the start target according to the sorting and marking results of S11;

[0106] When n (n ≥ 2) chillers need to be started during a certain period of time the next day, the total load Q of the period is calculated based on the prediction result of S12. n Then, taking the minimum total energy consumption of n chillers as the optimization goal, the PSO algorithm is used to solve the load rate of each chiller when the total energy consumption of n chillers is minimized:

[0107] PLR=(PLR1,PLR2,…,PLR n);

[0108] Among them, the total energy consumption of n chillers is:

[0109]

[0110] Where PLR i is the load factor of the i-th chiller, COP i is the operating energy efficiency of the i-th chiller, Q i is the rated cooling capacity of the i-th chiller, i = 1, 2, ..., n;

[0111] The optimization constraints of the PSO algorithm are:

[0112] 0 <PLR i <1(i=1,2,…,n);

[0113]

[0114] After determining the load rate of each chiller according to the optimization results of the PSO algorithm, the chiller with the highest operating efficiency at each load rate is selected as the start-up target based on the sorting and marking results of S11.

[0115] Embodiment 2

[0116] The embodiment of the present invention provides an energy-saving optimization control system for a central air-conditioning chiller, which is used to implement the method described in the first embodiment. The embodiment specifically includes:

[0117] A data acquisition module is used to collect and store historical operation data of the chillers in the central air conditioner, outdoor meteorological data and building work schedule; the outdoor meteorological data includes outdoor temperature and outdoor relative humidity; the historical operation data of the chillers includes the start time, shutdown time, maintenance records of each chiller, and load rate and operation energy efficiency during the working period;

[0118] The chiller load distribution optimization module is used to provide an optimized working strategy for the chiller after the data acquisition module has collected at least one year's worth of data, based on various known data, so as to reduce the overall energy consumption of the chiller;

[0119] The chiller control module is used to control each chiller to turn on or off in different time periods according to the optimization working strategy provided by the chiller load distribution optimization module, so as to distribute the total load to the turned-on chillers.

[0120] Furthermore, the data acquisition module specifically includes: a chiller data acquisition device, an outdoor meteorological data acquisition device and an industrial computer;

[0121] The chiller data collection device is connected to each chiller and is used to collect the start time, shut down time, maintenance records, and load rate and operating energy efficiency of each chiller during operation;

[0122] The outdoor meteorological data collection device is arranged in an outdoor space and is used to collect outdoor temperature and outdoor relative humidity;

[0123] The industrial computer is connected to the chiller data acquisition device and the outdoor meteorological data acquisition device through a network, and is used to classify, summarize and store the data collected by the chiller data acquisition device and the outdoor meteorological data acquisition device.

[0124] Furthermore, the chiller control module is also used to optimize the chiller's working strategy by adopting a rotation working strategy when the data collection module has not collected a full year's worth of data;

[0125] The rotation work strategy specifically includes:

[0126] S21. According to the collected historical operation data of the chillers, the cumulative operation time t of each chiller after the most recent maintenance is counted;

[0127] S22, sorting the chillers in order of the accumulated running time t from short to long;

[0128] S23, when it is necessary to start the chiller, according to the order of S22, the chiller with the shorter cumulative running time t is started first;

[0129] S24, after the chillers have been turned on for a period of time, re-ranking the accumulated running time t of each chiller, and when the chillers are turned on next time, the chillers with shorter accumulated running time t are selected according to the new ranking to be turned on;

[0130] S25. If a chiller is maintained, the accumulated running time t of the chiller is reset to zero and the chillers are rearranged.

[0131] Furthermore, in the chiller load distribution optimization module, the method for formulating the optimization working strategy is as follows:

[0132] S11. Draw the load rate-operation energy efficiency curve of each chiller according to the historical operation data of the chiller, and sort and mark the operation energy efficiency of all chillers in different distribution ranges of the load rate;

[0133] S12. Based on the historical operation data of the chiller and the outdoor meteorological data, a multi-step prediction model for building load is established and trained to predict the 24-hour hourly load of the building the next day;

[0134] S13, dividing the 24 hours of a day into multiple time periods, referring to the number of chillers turned on in each time period in the historical operation data of the chillers and the rated cooling capacity of each chiller turned on, formulating the primary working strategy of the chillers in each time period corresponding to the next day; the primary working strategy refers to the number of chillers that should be turned on in each time period of the next day, and the rated cooling capacity that each chiller turned on needs to achieve;

[0135] S14. Based on the primary working strategy determined in S13, the hourly load of the next day for 24 hours predicted in S12, and the ranking and marking results of the chiller operating efficiency obtained in S11, the optimization goal is to minimize the total energy consumption of the chillers that are turned on, and formulate an optimized working strategy for the chillers in each time period of the next day; the optimized working strategy refers to which chillers should be turned on in each time period of the next day.

[0136] Wherein, the S11 includes:

[0137] S111. For each chiller, based on the collected load rate PLR ​​and operating energy efficiency COP i , establish the following operation energy efficiency model and use the least squares method to solve the model parameters:

[0138] COP i =β0+β1PLR+β2PLR 2 ;

[0139] Where: β0, β1, β2 are model parameters;

[0140] S112. Draw the load rate-operation energy efficiency curve of each chiller according to the operation energy efficiency model of each chiller;

[0141] S113. According to the load rate-operating energy efficiency curve of each chiller, the load rate distribution interval of all chillers is obtained, and the load rate distribution interval is further divided into multiple mutually exclusive sub-intervals; in each sub-interval, the operating energy efficiency of all chillers is sorted and marked respectively.

[0142] The S12 includes:

[0143] S121. Based on the LSTM prediction model, outdoor temperature, outdoor relative humidity and building work schedule are selected as feature variables, and the total load of the chillers turned on in the building is selected as the output result to establish a multi-step prediction model for building load; the multi-step prediction model for building load is trained using the collected historical operation data of the chillers and outdoor meteorological data;

[0144] S122. Use the trained multi-step building load prediction model to predict the building's 24-hour hourly load for the next day (i.e., the total load for each hour in the 24 hours of the next day).

[0145] The S14 specifically includes:

[0146] When only one chiller needs to be started in a certain time period of the next day, the load rate of the time period is calculated according to the prediction result of S12, and then the chiller with the highest energy efficiency under the load rate is selected as the start target according to the sorting and marking results of S11;

[0147] When n (n ≥ 2) chillers need to be started during a certain period of time the next day, the total load Q of the period is calculated based on the prediction result of S12. n Then, taking the minimum total energy consumption of n chillers as the optimization goal, the PSO algorithm is used to solve the load rate of each chiller when the total energy consumption of n chillers is minimized:

[0148] PLR=(PLR1,PLR2,…,PLR n );

[0149] Among them, the total energy consumption of n chillers is:

[0150]

[0151] Where PLR i is the load factor of the i-th chiller, COP i is the operating energy efficiency of the i-th chiller, Q i is the rated cooling capacity of the i-th chiller, i = 1, 2, ..., n;

[0152] The optimization constraints of the PSO algorithm are:

[0153] 0 <PLR i <1(i=1,2,…,n);

[0154]

[0155] After determining the load rate of each chiller according to the optimization results of the PSO algorithm, the chiller with the highest operating efficiency at each load rate is selected as the start-up target based on the sorting and marking results of S11.

[0156] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. An energy-saving optimization control method for a central air-conditioning chiller, characterized in that: include: The data acquisition module collects and stores historical operation data of the chillers in the central air conditioner, outdoor weather data, and building work schedules; The outdoor meteorological data includes outdoor temperature and outdoor relative humidity; the historical operation data of the chiller includes the start time, shutdown time, maintenance records of each chiller, and the load rate and operating energy efficiency during the working period; After the data acquisition module has collected at least one year's worth of data, the following methods are used to optimize the chiller's operating strategy: S11. Draw the load rate-operation energy efficiency curve of each chiller according to the historical operation data of the chiller, and sort and mark the operation energy efficiency of all chillers in different distribution ranges of the load rate; S12. Based on the historical operation data of the chiller and the outdoor meteorological data, a multi-step prediction model for building load is established and trained to predict the 24-hour hourly load of the building the next day; S13, dividing the 24 hours of a day into multiple time periods, referring to the number of chillers turned on in each time period in the historical operation data of the chillers and the rated cooling capacity of each chiller turned on, formulating the primary working strategy of the chillers in each time period corresponding to the next day; the primary working strategy refers to the number of chillers that should be turned on in each time period of the next day, and the rated cooling capacity that each chiller turned on needs to achieve; S14, according to the primary working strategy determined in S13, the hourly load of the next day for 24 hours predicted in S12, and the ranking and marking results of the chiller operation efficiency obtained in S11, with the minimum total energy consumption of the chillers turned on as the optimization goal, formulate the optimal working strategy of the chillers in each time period of the next day; the optimal working strategy refers to which chillers should be turned on in each time period of the next day; S15. According to the optimized working strategy formulated in S14, corresponding chillers are started in different time periods of the next day.

2. The energy-saving optimization control method for a central air-conditioning chiller according to claim 1, characterized in that: The S11 includes: S111. For each chiller, based on the collected load rate PLR ​​and operating energy efficiency COP i , establish the following operation energy efficiency model and use the least squares method to solve the model parameters: COP i =β0+β1PLR+β2PLR 2 ; Where: β0, β1, β2 are model parameters; S112. Draw the load rate-operation energy efficiency curve of each chiller according to the operation energy efficiency model of each chiller; S113. According to the load rate-operating energy efficiency curve of each chiller, the load rate distribution interval of all chillers is obtained, and the load rate distribution interval is further divided into multiple mutually exclusive sub-intervals; in each sub-interval, the operating energy efficiency of all chillers is sorted and marked respectively.

3. The energy-saving optimization control method for a central air-conditioning chiller according to claim 1, characterized in that: The S12 includes: S121. Based on the LSTM prediction model, outdoor temperature, outdoor relative humidity and building work schedule are selected as feature variables, and the total load of the chillers turned on in the building is selected as the output result to establish a multi-step prediction model for building load; the multi-step prediction model for building load is trained using the collected historical operation data of the chillers and outdoor meteorological data; S122. Use the trained multi-step building load prediction model to predict the 24-hour hourly load of the building on the next day.

4. The energy-saving optimization control method for a central air-conditioning chiller according to claim 1, characterized in that: The S14 specifically includes: When only one chiller needs to be started in a certain time period of the next day, the load rate of the time period is calculated according to the prediction result of S12, and then the chiller with the highest energy efficiency under the load rate is selected as the start target according to the sorting and marking results of S11; When n (n ≥ 2) chillers need to be started during a certain period of time the next day, the total load Q of the period is calculated based on the prediction result of S12. n Then, taking the minimum total energy consumption of n chillers as the optimization goal, the PSO algorithm is used to solve the load rate of each chiller when the total energy consumption of n chillers is minimized: PLR=(PLR1,PLR2,…,PLR n ); Among them, the total energy consumption of n chillers is: Where PLR i is the load factor of the i-th chiller, COP i is the operating energy efficiency of the i-th chiller, Q i is the rated cooling capacity of the i-th chiller, i = 1, 2, ..., n; The optimization constraints of the PSO algorithm are: 0<PLR i <1(i=1,2,…,n); After determining the load rate of each chiller according to the optimization results of the PSO algorithm, further according to the sorting and marking results of S11, the chiller with the highest operating efficiency at each load rate is selected as the start-up target.

5. The energy-saving optimization control method for a central air-conditioning chiller according to claim 1, characterized in that: Also includes: When the data collection module has not collected a full year's worth of data, a rotation work strategy is used to optimize the chiller's work strategy; the rotation work strategy is: based on the operating time of each chiller during the maintenance cycle, the chiller with a shorter operating time is started first.

6. The energy-saving optimization control method for a central air-conditioning chiller according to claim 5, characterized in that: The rotation work strategy specifically includes: S21. According to the collected historical operation data of the chillers, the cumulative operation time t of each chiller after the most recent maintenance is counted; S22, sorting the chillers in order of the accumulated running time t from short to long; S23, when it is necessary to start the chiller, according to the order of S22, the chiller with the shorter cumulative running time t is started first; S24, after the chillers have been turned on for a period of time, re-ranking the accumulated running time t of each chiller, and when the chillers are turned on next time, the chillers with shorter accumulated running time t are selected according to the new ranking to be turned on; S25. If a chiller is maintained, the accumulated running time t of the chiller is reset to zero and the chillers are rearranged.

7. An energy-saving optimization control system for a central air-conditioning chiller, used to implement the energy-saving optimization control method for a central air-conditioning chiller according to any one of claims 1 to 6, characterized in that: include: Data collection module, used to collect and store historical operation data of chillers in central air conditioners, outdoor weather data and building work schedules; The outdoor meteorological data includes outdoor temperature and outdoor relative humidity; the historical operation data of the chiller includes the start time, shutdown time, maintenance records of each chiller, and the load rate and operating energy efficiency during the working period; The chiller load distribution optimization module is used to provide an optimized working strategy for the chiller after the data acquisition module has collected at least one year's worth of data, based on various known data, so as to reduce the overall energy consumption of the chiller; The chiller control module is used to control each chiller to be turned on or off in different time periods according to the optimization working strategy provided by the chiller load distribution optimization module, so as to distribute the total load to the turned-on chillers; In the chiller load distribution optimization module, the formulation method of the optimization working strategy is: S11. Draw the load rate-operation energy efficiency curve of each chiller according to the historical operation data of the chiller, and sort and mark the operation energy efficiency of all chillers in different distribution ranges of the load rate; S12. Based on the historical operation data of the chiller and the outdoor meteorological data, a multi-step prediction model for building load is established and trained to predict the 24-hour hourly load of the building the next day; S13, dividing the 24 hours of a day into multiple time periods, referring to the number of chillers turned on in each time period in the historical operation data of the chillers and the rated cooling capacity of each chiller turned on, formulating the primary working strategy of the chillers in each time period corresponding to the next day; the primary working strategy refers to the number of chillers that should be turned on in each time period of the next day, and the rated cooling capacity that each chiller turned on needs to achieve; S14. Based on the primary working strategy determined in S13, the hourly load of the next day for 24 hours predicted in S12, and the ranking and marking results of the chiller operating efficiency obtained in S11, the optimization goal is to minimize the total energy consumption of the chillers that are turned on, and formulate an optimized working strategy for the chillers in each time period of the next day; the optimized working strategy refers to which chillers should be turned on in each time period of the next day.

8. The energy-saving optimization control system for a central air-conditioning chiller according to claim 7, characterized in that: The data acquisition module includes: a chiller data acquisition device, an outdoor meteorological data acquisition device and an industrial computer; The chiller data collection device is connected to each chiller and is used to collect the start time, shut down time, maintenance records, and load rate and operating energy efficiency of each chiller during operation; The outdoor meteorological data collection device is arranged in an outdoor space and is used to collect outdoor temperature and outdoor relative humidity; The industrial computer is connected to the chiller data acquisition device and the outdoor meteorological data acquisition device through a network, and is used to classify, summarize and store the data collected by the chiller data acquisition device and the outdoor meteorological data acquisition device.

9. The energy-saving optimization control system for a central air-conditioning chiller according to claim 7, characterized in that: In the chiller load distribution optimization module, S14 specifically includes: When only one chiller needs to be started in a certain time period of the next day, the load rate of the time period is calculated according to the prediction result of S12, and then the chiller with the highest energy efficiency under the load rate is selected as the start target according to the sorting and marking results of S11; When n (n ≥ 2) chillers need to be started during a certain period of time the next day, the total load Q of the period is calculated based on the prediction result of S12. n Then, taking the minimum total energy consumption of n chillers as the optimization goal, the PSO algorithm is used to solve the load rate of each chiller when the total energy consumption of n chillers is minimized: PLR=(PLR1,PLR2,…,PLR n ); Among them, the total energy consumption of n chillers is: Where PLR i is the load factor of the i-th chiller, COP i is the operating energy efficiency of the i-th chiller, Q i is the rated cooling capacity of the i-th chiller, i = 1, 2, ..., n; The optimization constraints of the PSO algorithm are: 0<PLR i <1(i=1,2,…,n); After determining the load rate of each chiller according to the optimization results of the PSO algorithm, further according to the sorting and marking results of S11, the chiller with the highest operating efficiency at each load rate is selected as the start-up target.

10. The energy-saving optimization control system for a central air-conditioning chiller according to claim 7, characterized in that: The chiller control module is also used to optimize the chiller's working strategy by using a rotation working strategy when the data collection module has not collected a full year's worth of data; The rotation work strategy specifically includes: S21. According to the collected historical operation data of the chillers, the cumulative operation time t of each chiller after the most recent maintenance is counted; S22, sorting the chillers in order of the accumulated running time t from short to long; S23, when it is necessary to start the chiller, according to the order of S22, the chiller with the shorter cumulative running time t is started first; S24, after the chillers have been turned on for a period of time, re-ranking the accumulated running time t of each chiller, and when the chillers are turned on next time, the chillers with shorter accumulated running time t are selected according to the new ranking to be turned on; S25. If a chiller is maintained, the accumulated running time t of the chiller is reset to zero and the chillers are rearranged.

Images