CN115796055B - Optimized operation adjusting method based on complete air conditioning system simulation model - Google Patents
Optimized operation adjusting method based on complete air conditioning system simulation model Download PDFInfo
- Publication number
- CN115796055B CN115796055B CN202310036496.7A CN202310036496A CN115796055B CN 115796055 B CN115796055 B CN 115796055B CN 202310036496 A CN202310036496 A CN 202310036496A CN 115796055 B CN115796055 B CN 115796055B
- Authority
- CN
- China
- Prior art keywords
- air conditioning
- conditioning system
- simulation model
- water
- room
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004378 air conditioning Methods 0.000 title claims abstract description 89
- 238000004088 simulation Methods 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000005265 energy consumption Methods 0.000 claims abstract description 13
- 238000005457 optimization Methods 0.000 claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 238000010801 machine learning Methods 0.000 claims abstract description 10
- 230000006870 function Effects 0.000 claims abstract description 7
- 238000012360 testing method Methods 0.000 claims abstract description 6
- 230000007246 mechanism Effects 0.000 claims abstract description 5
- 238000013507 mapping Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims abstract description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 127
- 150000001875 compounds Chemical class 0.000 claims description 32
- 239000000498 cooling water Substances 0.000 claims description 24
- 238000001816 cooling Methods 0.000 claims description 13
- 230000033228 biological regulation Effects 0.000 claims description 10
- 238000007710 freezing Methods 0.000 claims description 8
- 230000008014 freezing Effects 0.000 claims description 8
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims description 5
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 abstract description 3
- 239000003570 air Substances 0.000 description 17
- 230000001143 conditioned effect Effects 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 6
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 5
- 229910052799 carbon Inorganic materials 0.000 description 5
- 239000008400 supply water Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000004134 energy conservation Methods 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 2
- 230000017525 heat dissipation Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 239000012080 ambient air Substances 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009530 blood pressure measurement Methods 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004821 distillation Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 238000004781 supercooling Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Air Conditioning Control Device (AREA)
Abstract
An optimization operation adjusting method based on a complete air conditioning system simulation model abstracts an air conditioning system into seven components and constructs the air conditioning system simulation model; fitting simulation model parameters; constructing a boundary condition by taking the lowest overall energy consumption of the air conditioning system as a target function and a physical mechanism of the operation of the air conditioning system; dividing historical data of the air conditioning system into a training set and a test set, and forming digital twin mapping of the historical running state of the air conditioning system through a deep machine learning algorithm; correcting the tail end requirement of the simulation model of the air conditioning system by utilizing the difference value between the indoor set temperature and the collected temperature of the air conditioning system; and outputting the adjusting parameters by using the air conditioning system simulation model to finish the optimal operation adjustment of the air conditioning system. The invention takes the whole energy consumption reduction of the system as a target, takes the set value meeting condition of the adjusted space as the indication of load deviation, and breaks through the limitation of simulating or predicting the load only by the rule learning of historical data.
Description
Technical Field
The invention belongs to the technical field of building energy operation intelligent systems, and particularly relates to an intelligent operation mode based on a complete simulation model of a building air conditioning system from a supply end to a demand end.
Background
According to international energy organization (IEA) related reports, carbon emissions from energy consumption during operation of a building account for 28% of the total emissions, with 2/3 coming from the rapidly increasing electricity usage. Since 2000, the power demand in buildings has increased at a rate 5 times the rate of decrease in carbon emission intensity in the power sector. If considering carbon emission of building materials and construction processes, the building carbon emission accounts for 39% of the total emission. Therefore, energy conservation and consumption reduction in the building operation stage are important components for achieving the strategic goal of 'double carbon'.
In the building operation stage, the energy consumption of an air conditioning system (HVAC) usually accounts for more than 30% -50% of the operation energy consumption of a public building. Because the air conditioning system is designed to meet the maximum requirement of a user, the air conditioning system is in a partial-load working state most of the time during actual use, so that the working efficiency of the air conditioning system is low and the energy consumption is high during constant-working-condition operation, and the following problems are brought along: the working condition adjusting capability is poor; the operation and maintenance cost is high; and a large amount of running data is lost, so that practical application cannot be obtained, and the like. Efficient regulation of the operational stages of a building is therefore required to address the high energy consumption and related problems.
Along with popularization and application of related technologies such as internet of things, digitalization and the like, a large amount of historical data can be accumulated in the building operation stage, and through deep machine learning combining the historical data and a physical mechanism, a more intelligent operation control mode, namely an intelligent system for building operation, can be formed under the conditions of meeting several requirements such as comfort, energy conservation, variable working condition regulation, continuous and stable operation, easy acceptance and grasp of personnel and the like. The building intelligent system is based on the building information system, and forms the intelligent operation ability of perception, transmission, memory, reasoning, judgment and decision for various kinds of building information, thereby the building gradually forms a whole with the coordination of people, building and environment.
In the prior art, some constituent devices of an air conditioning system, such as a water chilling unit and a water pump, apply a certain machine learning algorithm to collected historical data, and output operation parameters of the devices to perform optimal regulation and control. For example, chinese patent application 202110825277.8 discloses a machine learning-assisted operation control optimization method for a centralized chiller air conditioning system, which establishes a chiller air conditioning system model based on energy conservation and individualized equipment operation parameter constraints, and obtains an efficient energy-saving operation strategy for a chiller by using an optimization algorithm combining deep learning neural network prediction machine operation parameters and a particle swarm algorithm, thereby providing a guidance for optimization of building operation. However, the optimization and control in the prior art may cause situations such as energy saving achieved by sacrificing comfort, and realizing a local optimal solution rather than an overall optimal solution, because only a part of devices of the system is targeted, not a complete system.
Disclosure of Invention
The invention aims to provide an optimized operation regulation method based on a complete air conditioning system simulation model, which comprises the steps of constructing a complete system, bringing the comfort level of a regulated space of a terminal into a regulation boundary condition, taking the reduction of the overall energy consumption of the system as a target on the premise of meeting a terminal requirement, and breaking through the limitation of simulating or predicting a load only by regular learning of historical data by taking the set value meeting condition of the regulated space as an indication of load deviation.
The invention provides an optimal operation adjusting method based on a complete air conditioning system simulation model, which mainly comprises the following steps:
s01, abstracting a complete air conditioning system into seven components, wherein the components are mutually associated and jointly constructed into an air conditioning system simulation model; the seven components comprise a water chilling unit, a water pump, a cooling tower, a bypass valve, terminal equipment, a room and a chilled water pipe network;
step S02, fitting parameters of a simulation model of the air conditioning system through a deep machine learning algorithm according to actual operation data of the air conditioning system, and carrying out optimization adjustment on the parameters according to model precision;
step S03, aiming at the air conditioning system simulation model, establishing boundary conditions by taking the lowest overall energy consumption of the air conditioning system as a target function and taking a physical mechanism of the operation of the air conditioning system;
step S04, dividing the historical data of the air conditioning system into a training set and a testing set, applying the air conditioning system simulation model, and forming digital twin mapping of the historical running state of the air conditioning system through a deep machine learning algorithm;
step S05, correcting the tail end requirement of the air conditioning system simulation model by using the difference value between the indoor set temperature and the collected temperature of the air conditioning system to obtain the correction of the room in the air conditioning system simulation model;
and S06, in actual operation, outputting adjusting parameters by applying the air conditioning system simulation model established and corrected according to the steps S01-S05, providing the adjusting parameters for an information system of the air conditioning system to execute regulation and control actions, and finishing the optimized operation adjustment of the air conditioning system.
Further, the water pump comprises a chilled water pump and a cooling water pump; the terminal equipment comprises an air handling unit AHU and a fan coil.
Further, in step S02, 5 indexes of a Mean Absolute Error (MAE), a percentage of mean absolute error (MAPE), a Root Mean Square Error (RMSE), a coefficient of determination (R2), and a coefficient of variation of the root mean square error (CV-RMSE) are used as evaluation indexes of prediction accuracy of the simulation model of the air conditioning system, and the parameters are optimized and adjusted.
Further, in step S03, the objective function is constructed as follows:
in the formula (I), the compound is shown in the specification,P total, sys is the total power of the system;P ichiller, is a firstiInputting power to a water chilling unit;P ch,pump 、 P c, pump the power of a freezing water pump and the power of a cooling water pump are respectively;P fan,i is as followsiThe input power of the desk fan;P AHU the power of an air handling unit for the end equipment;P fc,i the power of the end fan coil.
Further, in step S05, the indoor dry bulb temperature of the room is set toThe difference between the collected values, the set value of the indoor wet bulb temperature and the difference between the collected values are used as indications of the real load demand of the tail end, the tail end demand is proportionally adjusted through the difference, and the output value is outputΔQ room And according to the output valueΔQ room And correcting the air conditioning system simulation model.
Further, in step S06, the adjusting parameters include: the number of running cold machines and the water supply temperature, the number and the frequency of running freezing water pumps, the number of running cooling tower fans, the opening of a bypass valve, the number of running terminal AHU, the number of running terminal fan coils, a set value of room temperature dry bulb temperature and a set value of room temperature wet bulb temperature.
By adopting the optimal operation adjusting method based on the complete air conditioning system simulation model, the energy-saving effect of the air conditioning system is brought by two modes on the premise of ensuring the comfort level of the adjusted space: the operation parameters of all the components of the air conditioning system are optimized and adjusted, and the aim of minimizing the overall energy consumption is fulfilled to achieve the energy-saving effect; and the condition of supercooling supply in the load is identified by taking the deviation between the set value and the actual value of the tail end regulated space as an indication, and the energy-saving effect is achieved after the optimal regulation. When the traditional building control system is used for dealing with the change of actual working conditions, the conditions of lag in adjustment and incapability of meeting the current load exist, manual judgment is relied on, and adjustment parameters are input, so that the running state of the system is unstable, and the stability and the continuity of the running of the system can be ensured to the maximum extent through the intelligent adjustment mode; the highly automatic intelligent operation of the system enables operation and maintenance personnel to accept and grasp easily, and meanwhile, beneficial measures are easy to transfer and accumulate. The invention fully utilizes a large amount of historical data in the operation of the air-conditioning system, reflects the performance of equipment and the system, and feeds back the performance to the optimization and adjustment in the operation, so that the data value is applied; by applying a large amount of historical data, the device sample information is replaced to a certain extent, and the device can be applied to different projects after system configuration, including different energy forms, different scales, different coverage ranges and the like, so that the reproducibility of application is improved.
Drawings
For a more complete understanding of the present invention, reference is now made to the following descriptions taken in conjunction with the accompanying drawing, in which:
FIG. 1 is a schematic flow chart of an optimal operation adjustment method based on a complete air conditioning system simulation model according to the present invention;
FIG. 2 is a schematic diagram of the components of the air conditioning system of the present invention.
Detailed Description
For the purpose of illustrating the invention, its technical details and its practical application to thereby enable one of ordinary skill in the art to understand and practice the invention, reference will now be made in detail to the embodiments of the present invention with reference to the accompanying drawings. It is to be understood that the embodiments described herein are merely illustrative and explanatory of the invention and are not restrictive thereof.
The invention provides an optimal operation adjusting method based on a complete air conditioning system simulation model, which mainly comprises the following steps with reference to figure 1:
s01, abstracting a complete air conditioning system into seven components, wherein the components are mutually associated and jointly constructed into an air conditioning system simulation model; the seven components comprise a water chilling unit 1, a water pump 2, a cooling tower 3, a bypass valve 4, a terminal device 5, a room 6 and a chilled water pipe network 7; as shown in particular in fig. 2.
Specifically, the water pump 2 includes a chilled water pump and a cooling water pump; the terminal equipment 5 comprises an air handling unit AHU, a fan coil and the like.
The mathematical relational model adopted by each component part is as follows:
(1) A water chilling unit 1:
P ichiller, = c 1 + c 2 × PLR + c 3 × PLR 2 + c 4 × T chw,o + c 5 × T chw,o 2 + c 6 × T cw,i + c 7 ×T cw,i 2
+ c 8 × PLR× T chw,o + c 9 × PLR× T cw,i + c 10 × T chw,o × T cw,i + c 11 × PLR × T chw,o × T cw,i
in the formula (I), the compound is shown in the specification,P ichiller, is a firstiThe table water chilling unit inputs power, kW;PLRthe partial load rate of the unit;T chw,o supplying water temperature to the chilled water;T cw,i the temperature of the cooling water return water is set;c 1 ~c 11 are all model parameters.
(2) And (3) a water pump 2:
in the formula (I), the compound is shown in the specification,P pump the input power of the water pump;fkW is water pump power;f 0 is power frequency, 50Hz;Gd, carrying out water pump flow, and m and h;
b 1 ~b 3 are all model parameters.
(3) Cooling tower 3:
frequency conversion fan:
a fixed-frequency fan:
in the formula (I), the compound is shown in the specification,P fan,i is as followsiThe input power of the desk fan;P irated, is as followsiRated power of the counter fan.
(4) Bypass valve 4:
the relationship between the valve resistance and the water pressure difference of the bypass valve 4 is as follows:
S = ΔP / G 2
in the formula (I), the compound is shown in the specification,Sin order to provide resistance to the water valve,ΔPis the pressure drop across the water valve;Gis the flow of water through the water valve.
(5) The end device 5:
in the formula (I), the compound is shown in the specification,P i the input power of the ith station terminal equipment;P rated,i is the rated power of the ith end-point device.
Wherein the above mathematical relation of the terminal device 5 can be adjusted for specific situations.
(6) Room 6:
T a, h = T a,s +φ havc Q room
Q room = Q AHU + Q fc
Q AHU = c w ρ w G w (T w,o - T w,i )
Q fc = c w ρ w G w (T w,o - T w,i )
c w ρ w G w (T w,o - T w,i )= G air,s ρ a (h o - h i )
in the formula (I), the compound is shown in the specification,T a, h the return air temperature is DEG C;T a,s air supply temperature, DEG C;φ havc the coefficient of heat exchange performance of the room to be adjusted is;Q room the heat exchange quantity of the room to be conditioned;Q AHU the cooling capacity of the air handling unit of the terminal equipment is supplied;Q fc the cooling capacity of the fan coil of the terminal equipment;c w is the constant pressure specific heat of the frozen water;ρ w is the density of the chilled water;G w the amount of the frozen water is;T w,i 、T w,o respectively the supply temperature of the chilled water and the return temperature of the chilled water at DEG C;G air,s d, carrying out air blowing, and carrying out m ethanol distillation/h;ρ a is the density of ambient air;h i is the air supply enthalpy value of the end equipment,h o the return air enthalpy of the end equipment.
(7) Chilled water pipe network 7:
a chilled water pipe network 7 model adopts a matrix method, the number of water pipe network branches is B, the number of nodes is N +1, and the pressure matrix equation of the water network is as follows:
B chw ΔH = 0
in the formula (I), the compound is shown in the specification,B chw is a basic loop matrix of a freezing water network, and a (B-N) multiplied by B order matrix;ΔHis the branch pressure drop column vector, kPa.
The relation between the pressure measurement value of each branch and the pressure head, and the dynamic pressure drop neglected by each branch pipe section:
H = (p 2 - p 1 ) / ρg+(v 2 ² - v 1 ²)/2g + z 2 - z 1
in the formula (I), the compound is shown in the specification,His a branch pressure head, mH 2 O ；p 2 Is the pressure at the end of the pipeline;p 1 is the pressure at the starting end of the pipeline;ρis the density of water in the pipeline; g is the acceleration of gravity;v 2 the flow rate of water at the end of the pipeline;v 1 the water flow rate is the initial end of the pipeline;z 2 is the end of a branchElevation;z 1 is the elevation of the starting end of the branch.
A water pump pressure head model:
in the formula (I), the compound is shown in the specification,Hfor pump lift, mH 2 O；GThe water flow of the water pump;nthe number of the water pumps is;a 1 ~a 3 are all model parameters.
The components in the air conditioning system can show the association relationship of the air conditioning system through the data associated with each other. For example, demand cooling load-associated room return air temperature, room temperature supply air temperature-associated end heat exchange amount-associated cooling amount-associated cold water supply temperature, freezer pump water flow.
And S02, fitting parameters of the air conditioning system simulation model according to actual operation data of the air conditioning system through a deep machine learning algorithm, and carrying out optimization adjustment on the parameters according to model precision.
The Mean Absolute Error (MAE), the percentage of mean absolute error (MAPE), the Root Mean Square Error (RMSE), and the coefficient of determination (R) 2 ) And 5 indexes of a variation coefficient (CV-RMSE) of a root mean square error are used as evaluation indexes of prediction accuracy of the simulation model of the air conditioning system, and when the index value is greatly deviated, the evaluation indexes are used as starting conditions of model parameter optimization until the evaluation indexes reach a reasonable range through an optimization result.
The MAE, MAPE, RMSE and CV-RMSE can reflect the deviation degree between the predicted value and the actual value, and the smaller the value of the MAE, MAPE, RMSE and CV-RMSE is, the higher the model prediction accuracy is; r is 2 The degree of fit of the model may be reflected. R is 2 The closer the value of (a) is to 1, the better the fitting of the model to the observed values. The calculation method of each index is as follows:
in the formula (I), the compound is shown in the specification,y i is an actual value;
is predicted value and is based on>
In order to test the actual average value of the set,mthe total number of data samples in the test set.
For the condition that the end data in the actual operation process of the air conditioning system is incomplete, partial end data can represent the whole end load data by weighted average of information such as the use area, the operation power and the like.
And S03, aiming at the air conditioning system simulation model, establishing boundary conditions by taking the lowest overall energy consumption of the air conditioning system as a target function and taking a physical mechanism of the operation of the air conditioning system.
Firstly, the objective function is constructed in the following way:
in the formula (I), the compound is shown in the specification,P total, sys is the total power of the system;P ichiller, is composed ofFirst, theiInputting power to a water chilling unit;P ch,pump 、 P c, pump the power of a freezing water pump and the power of a cooling water pump are respectively;P fan,i is as followsiThe input power of the desk fan;P AHU the power of an air handling unit for the end equipment;P fc,i the power of the end fan coil.
Secondly, the boundary conditions include:
(1) The constraint of equation:
by heat conservation, the heat dissipation value of the condenser is equal to the sum of the cooling capacity and the power of the water chilling unit, and the formula is expressed as follows:
Q
c
=Q
e
+ P
chiller
in the formula (I), the compound is shown in the specification,Q c the heat dissipation capacity of the condensation side;Q e the refrigeration capacity is supplied to the freezing side.
Conservation of mass:
G
bypass
= G
chw
- G
AHU
- G
fc
in the formula (I), the compound is shown in the specification,G bypass the flow rate of the chilled water passing through the bypass valve;G chw the total flow rate of the chilled water;G AHU is the water flow through the terminal air handling unit;G fc is the flow of water through the end fan coil.
The relative temperature, pressure equality constraints derived from heat and mass conservation:
and (3) restricting the temperature of a bypass valve:
in the formula (I), the compound is shown in the specification,T ch,i the return water temperature of the chilled water is set;T chw,AHU the temperature of return water flowing through the air treatment unit;G AHU the flow rate of the chilled water is that of the air handling unit;T chw,fc the temperature of the return water flowing through the fan coil pipe;G fc the chilled water flow rate for the fan coil;T chw,o the temperature of the return water flowing through the bypass valve;G bypass the flow rate of the chilled water flowing through the bypass valve;G chw is the total flow of chilled water.
Temperature constraint of the chilled water:
T
chw,i
= T
chw,o
+ΔT
chw
in the formula (I), the compound is shown in the specification,T chw,i the temperature of the chilled water return water is set;T chw,o supplying water temperature to the chilled water;ΔT chw the temperature difference of the supply water and the return water for the chilled water.
Cooling water temperature constraint:
T
cw,i
= T
cw,o
+ΔT
cw
in the formula (I), the compound is shown in the specification,T cw,i the temperature of the cooling water return water is set;T cw,o supplying water temperature to the cooling water;ΔT cw the temperature difference of the cooling water supply and return water. 8230; 8230please explain the meaning of parameters.
Pressure restraint of a chilled water pipe network:
B chw ΔH = 0
in the formula (I), the compound is shown in the specification,B chw is a basic loop matrix of a freezing water network, and a (B-N) multiplied by B order matrix;ΔHis a branch pressure dropColumn vector, kPa.
(2) Inequality boundary conditions:
the cold energy supply constraint condition of the single water chilling unit is as follows:
Q chiller,min ≤ Q chiller,i ≤ Q rated
in the formula (I), the compound is shown in the specification,Q chiller,min a cold supply quantity lower limit value is supplied to the water chiller;Q chiller,i supplying cold energy to the water chiller;Q rated the rated cooling capacity of the water chilling unit is provided.
The single machine flow constraint conditions of the water chilling unit are as follows:
G chw,min ≤ G chw ≤ G chw,max
in the formula (I), the compound is shown in the specification,G chw,min a water flow low limit value of chilled water of a water chilling unit;G chw the flow rate of chilled water of a water chilling unit;G chw,max the flow rate of the chilled water of the water chilling unit is high.
The water chilling unit part load rate constraint conditions are as follows:
PLR min ≤ PLR ≤ 1
in the formula (I), the compound is shown in the specification,PLR min the water chilling unit load factor is a low limit value of the partial load factor of the water chilling unit;PLRis the partial load rate of the water chilling unit.
The chilled water supply water temperature constraint condition is as follows:
T
chw,min
≤ T
chw,o
≤ T
chw,max
in the formula (I), the compound is shown in the specification,T chw,min a lower limit value of the water supply temperature for the chilled water;T chw,o supplying water temperature to the chilled water;T chw,max high temperature of water supplied to chilled waterAnd (4) limiting values.
Cooling water supply temperature constraint conditions:
T
cw,min
≤ T
cw,i
≤ T
cw,max
in the formula (I), the compound is shown in the specification,T cw,min a lower limit value of the water supply temperature for the cooling water;T cw,i supplying water temperature to the cooling water;T cw,max a high limit value of the water temperature for the cooling water.
The chilled water supply and return water temperature difference constraint condition is as follows:
ΔT chw, min ≤ΔT chw ≤ΔT chw, max
in the formula (I), the compound is shown in the specification,ΔT chw, min a low limit value of the temperature difference of the supply water and the return water for the chilled water;ΔT chw supplying and returning water temperature difference for chilled water;Δ T chw, max and the high limit value of the temperature difference of the supply water and the return water for the chilled water.
Cooling water supply and return water temperature difference constraint conditions:
ΔT cw, min ≤ΔT cw ≤ΔT cw, max
in the formula (I), the compound is shown in the specification,ΔT cw, min a low limit value of temperature difference for supplying and returning cooling water;ΔT cw supplying and returning water temperature difference for cooling water;Δ T cw, max and the high limit value of the temperature difference of the cooling water supply and return water.
The opening degree constraint condition of the bypass valve is as follows:
0 ≤ L ≤ 100
in the formula (I), the compound is shown in the specification,Lis the percentage of the valve opening.
Frequency constraint condition of the refrigerating pump:
f chw,min ≤ f chw ≤ 50
in the formula，f chw,min The frequency lower limit value of the chilled water pump;f chw is the operating frequency of the chilled water pump.
Cooling pump frequency constraint condition:
f cw,min ≤ f cw ≤ 50
in the formula (I), the compound is shown in the specification,f cw,min the frequency lower limit value of the cooling water pump;f cw the operating frequency of the cooling water pump.
And (3) flow constraint conditions of the fixed-frequency cooling water pump:
G cw,min ≤ G cw ≤ G cw,max
in the formula (I), the compound is shown in the specification,G cw,min the flow rate of the fixed-frequency cooling water pump is a low limit value;G cw the water flow rate of the fixed-frequency cooling water pump;G cw,max the flow rate of the fixed-frequency cooling water pump is a high limit value.
Worst end water pressure difference constraint conditions:
ΔP min ≤ΔP
in the formula (I), the compound is shown in the specification,ΔP min the minimum value of the pressure difference at the worst end;ΔPthe worst end pressure difference.
Indoor dry bulb temperature constraint conditions:
T a,h,d,min ≤ T a,h,d ≤ T a,h,d,max
in the formula (I), the compound is shown in the specification,T a,h,d,min the temperature is the low limit value of the dry bulb temperature in the room to be conditioned;T a,h,d is the dry bulb temperature in the room to be conditioned;T a,h,d,max is the high value of the dry bulb temperature in the room to be conditioned.
Indoor wet bulb temperature constraint conditions:
T a,h,w,min ≤ T a,h,w ≤ T a,h,w, max
in the formula (I), the compound is shown in the specification,T a,h,w,min the lower limit value of the wet bulb temperature in the room to be conditioned;T a,h,w is the wet bulb temperature in the conditioned room;T a,h,w, max is the upper limit value of the wet bulb temperature in the room to be conditioned.
And S04, dividing the historical data of the air conditioning system into a training set and a testing set, applying the air conditioning system simulation model, and forming digital twin mapping of the historical running state of the air conditioning system through a deep machine learning algorithm.
And S05, correcting the tail end requirement of the air-conditioning system simulation model by using the difference value between the indoor set temperature and the collected temperature of the air-conditioning system to obtain the correction of the room 6 in the air-conditioning system simulation model.
Specifically, the difference between the indoor dry bulb temperature set value and the collected value of the room 6 and the difference between the indoor wet bulb temperature set value and the collected value are used as indications of the real end demand load, the end demand is proportionally adjusted through the difference, and the output value is outputΔ Q room And according to the output valueΔQ room And correcting the air conditioning system simulation model.
And S06, in actual operation, outputting adjusting parameters by applying the air conditioning system simulation model established and corrected according to the steps S01-S05, providing the adjusting parameters for an information system of the air conditioning system to execute regulation and control actions, and finishing the optimized operation adjustment of the air conditioning system.
Specifically, the adjustment parameters include the parameters listed in the following output adjustment parameter table.
Output regulation parameter table
Claims (7)
1. An optimized operation adjusting method based on a complete air conditioning system simulation model mainly comprises the following steps:
s01, abstracting a complete air conditioning system into seven components, wherein the components are mutually associated and jointly constructed into an air conditioning system simulation model; the seven components comprise a water chilling unit, a water pump, a cooling tower, a bypass valve, terminal equipment, a room and a chilled water pipe network;
step S02, fitting parameters of a simulation model of the air conditioning system through a deep machine learning algorithm according to actual operation data of the air conditioning system, and carrying out optimization adjustment on the parameters according to model precision;
step S03, aiming at the air conditioning system simulation model, establishing boundary conditions by taking the lowest overall energy consumption of the air conditioning system as a target function and taking a physical mechanism of the operation of the air conditioning system;
step S04, dividing the historical data of the air conditioning system into a training set and a testing set, applying the air conditioning system simulation model, and forming digital twin mapping of the historical running state of the air conditioning system through a deep machine learning algorithm;
step S05, correcting the tail end requirement of the air conditioning system simulation model by utilizing the difference value between the indoor set temperature and the collected temperature of the air conditioning system to obtain the correction of the room in the air conditioning system simulation model;
and S06, in actual operation, outputting adjusting parameters by applying the air conditioning system simulation model established and corrected according to the steps S01-S05, providing the adjusting parameters for an information system of the air conditioning system to execute regulation and control actions, and finishing the optimized operation adjustment of the air conditioning system.
2. The method of claim 1, wherein the water pump comprises a chilled water pump, a chilled water pump.
3. The method of claim 1, wherein the end equipment comprises an Air Handling Unit (AHU), a fan coil.
4. The method according to claim 1, wherein in step S02, 5 indexes of mean absolute error MAE, percent of mean absolute error MAPE, root mean square error RMSE, coefficient of variation CV-RMSE of decision R2 and root mean square error are used as the evaluation indexes of the prediction accuracy of the simulation model of the air conditioning system, so as to optimize and adjust the parameters.
5. The method according to claim 1, wherein in step S03, the objective function is constructed as follows:
in the formula (I), the compound is shown in the specification,P total, sys total power of the air conditioning system;P ichiller, is as followsiInputting power by a water chilling unit;P ch,pump i, 、P c, pump,i are respectively the firstiThe power of a table freezing water pump and a cooling water pump;P fan,i is as followsiThe input power of the desk fan;P AHU i, is a firstiThe power of the air handling unit of the station end equipment;P fc,i is as followsiPower of the fan coil at the end of the station.
6. The method according to claim 1, wherein in step S05, the difference between the indoor dry bulb temperature setting value and the collected value of the room and the difference between the indoor wet bulb temperature setting value and the collected value are used as the indication of the real end demand load, the end demand is proportionally adjusted through the difference, and the room heat exchange amount correction value is outputΔQ room And correcting the value according to the heat exchange amount of the roomΔQ room And correcting the air conditioning system simulation model.
7. The method of claim 1, wherein in step S06, the adjusting parameters comprise: the number of running cold machines and the water supply temperature, the number and the frequency of running freezing water pumps, the number of running cooling tower fans, the opening of a bypass valve, the number of running terminal air handling unit AHU, the number of running terminal fan coil pipes, a set value of room temperature dry bulb temperature and a set value of room temperature wet bulb temperature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310036496.7A CN115796055B (en) | 2023-01-10 | 2023-01-10 | Optimized operation adjusting method based on complete air conditioning system simulation model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310036496.7A CN115796055B (en) | 2023-01-10 | 2023-01-10 | Optimized operation adjusting method based on complete air conditioning system simulation model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115796055A CN115796055A (en) | 2023-03-14 |
| CN115796055B true CN115796055B (en) | 2023-04-07 |
Family
ID=85428917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310036496.7A Active CN115796055B (en) | 2023-01-10 | 2023-01-10 | Optimized operation adjusting method based on complete air conditioning system simulation model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115796055B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503388A (en) * | 2016-11-09 | 2017-03-15 | 东南大学 | air conditioning system characteristic recognition method |
| CN106529021A (en) * | 2016-11-09 | 2017-03-22 | 东南大学 | Air conditioning system simulation method based on feature recognition |
| CN111442478A (en) * | 2020-03-10 | 2020-07-24 | 珠海派诺科技股份有限公司 | Air conditioning system optimization control method, intelligent terminal and storage device |
| CN112084707A (en) * | 2020-09-02 | 2020-12-15 | 西安建筑科技大学 | Refrigeration machine room energy-saving optimization method and system based on variable flow decoupling of chilled water and cooling water |
| CN113536525A (en) * | 2021-04-16 | 2021-10-22 | 广州地铁设计研究院股份有限公司 | Global optimal energy-saving control method for central air conditioner |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020107851A1 (en) * | 2018-11-29 | 2020-06-04 | 天津大学 | Low-cost commissioning method and system for air conditioning system based on existing large-scale public building |
-
2023
- 2023-01-10 CN CN202310036496.7A patent/CN115796055B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503388A (en) * | 2016-11-09 | 2017-03-15 | 东南大学 | air conditioning system characteristic recognition method |
| CN106529021A (en) * | 2016-11-09 | 2017-03-22 | 东南大学 | Air conditioning system simulation method based on feature recognition |
| CN111442478A (en) * | 2020-03-10 | 2020-07-24 | 珠海派诺科技股份有限公司 | Air conditioning system optimization control method, intelligent terminal and storage device |
| CN112084707A (en) * | 2020-09-02 | 2020-12-15 | 西安建筑科技大学 | Refrigeration machine room energy-saving optimization method and system based on variable flow decoupling of chilled water and cooling water |
| CN113536525A (en) * | 2021-04-16 | 2021-10-22 | 广州地铁设计研究院股份有限公司 | Global optimal energy-saving control method for central air conditioner |
Non-Patent Citations (1)
| Title |
|---|
| 闫军威 等.商场过渡季节中央空调冷源系统运行参数优化研究.制冷与空调(四川).2016,30(06),第677-683、395页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115796055A (en) | 2023-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108413567A (en) | Central hollow adjusting based on Internet of Things takes optimization method and system | |
| CN100362295C (en) | Automatic volume regulating and controlling method for gas-burning machine heat pump | |
| CN109945402A (en) | A kind of central air conditioning water system power-economizing method | |
| CN110895016A (en) | Fuzzy self-adaptive based energy-saving group control method for central air-conditioning system | |
| CN115325682B (en) | Optimal control method and device for monitoring performance of efficient intelligent refrigeration machine room | |
| CN113739371B (en) | Central air conditioning system based on cloud cooperation and control method thereof | |
| CN104160217A (en) | Air-conditioning control device and storage medium | |
| CN116558049A (en) | System and optimal control method based on central air conditioner load dynamic prediction | |
| CN116398994B (en) | Water chilling unit group control optimization method based on load prediction | |
| CN112413823A (en) | Distributed energy optimization management method of central air conditioning system in demand response mode | |
| CN114459133A (en) | Energy-saving control method and energy-saving control system for central air-conditioning system | |
| CN115049141A (en) | Control method and control device for refrigeration system and refrigeration system | |
| CN115903712A (en) | Energy-saving optimization method and optimization control system suitable for industrial refrigeration system | |
| CN111415036B (en) | Load optimization distribution method for parallel connection cold machines of central air-conditioning system | |
| CN115796055B (en) | Optimized operation adjusting method based on complete air conditioning system simulation model | |
| CN117366799A (en) | Control method of building cold source system | |
| CN104949274B (en) | A kind of air quantity variable air conditioner handpiece Water Chilling Units double loop control method | |
| CN114135983B (en) | Combined optimization scheduling method and system for water cooling unit and air-cooled heat pump unit | |
| Xiao et al. | Energy saving analysis of refrigeration room group control based on kernel ridge regression algorithm | |
| CN113719929B (en) | Method and system for optimizing and controlling integrity of lithium bromide air conditioning system | |
| CN115573926A (en) | Machine room water pump energy-saving operation method combining BP neural network fitting characteristic curve | |
| Zheng | Research on energy-saving control and optimisation of air conditioning system based on genetic algorithm | |
| CN220044029U (en) | Water-cooling energy station energy-saving system based on big data analysis | |
| CN220287880U (en) | Energy-saving control system of refrigeration house evaporation system | |
| CN220254941U (en) | Refrigerating system and liquid cooling equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An optimized operation and regulation method based on a complete air conditioning system simulation model Granted publication date: 20230407 Pledgee: Shijiazhuang Luquan Rural Commercial Bank Co.,Ltd. Pledgor: BEIJING YUNLU TECHNOLOGY CO.,LTD. Registration number: Y2024980015341 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |