CN116956734A - Refrigeration station energy efficiency model fitting method and device - Google Patents
Refrigeration station energy efficiency model fitting method and device Download PDFInfo
- Publication number
- CN116956734A CN116956734A CN202310936790.3A CN202310936790A CN116956734A CN 116956734 A CN116956734 A CN 116956734A CN 202310936790 A CN202310936790 A CN 202310936790A CN 116956734 A CN116956734 A CN 116956734A
- Authority
- CN
- China
- Prior art keywords
- model
- energy efficiency
- pump
- cooling
- power model
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000005057 refrigeration Methods 0.000 title claims abstract description 38
- 238000001816 cooling Methods 0.000 claims abstract description 85
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 85
- 238000007710 freezing Methods 0.000 claims abstract description 7
- 230000008014 freezing Effects 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 34
- 238000012706 support-vector machine Methods 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 239000000498 cooling water Substances 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 10
- 239000012530 fluid Substances 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000010977 unit operation Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 abstract description 8
- 238000010801 machine learning Methods 0.000 abstract description 5
- 238000005265 energy consumption Methods 0.000 description 9
- 239000003507 refrigerant Substances 0.000 description 9
- 238000012549 training Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 239000007788 liquid Substances 0.000 description 5
- 238000004378 air conditioning Methods 0.000 description 4
- 238000012417 linear regression Methods 0.000 description 4
- 238000013178 mathematical model Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000009977 dual effect Effects 0.000 description 2
- 238000004134 energy conservation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000005251 gamma ray Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses a refrigeration station energy efficiency model fitting method and device, which are used for obtaining a water chilling unit running power model, a refrigerating pump running power model, a cooling tower fan running power model and refrigerating capacity of the water chilling unit; constructing a total running power model of the refrigeration station for the water chilling unit running power model, the freezing pump running power model, the cooling pump running power model and the cooling tower fan running power model; establishing a refrigeration station energy efficiency model according to the refrigeration capacity and the total running power model; the invention combines the data driving and physical modeling methods, fully plays the respective advantages of the machine learning and physical modeling methods, improves the fitting precision and accuracy of the energy efficiency model of the refrigeration station, and lays the foundation of the subsequent energy saving and optimization control of the refrigeration station.
Description
Technical Field
The invention belongs to the technical field of energy efficiency analysis of refrigeration stations, and particularly relates to a refrigeration station energy efficiency model fitting method and device.
Background
The air conditioning system is more and more widely applied to various buildings, the air conditioning system also causes a large amount of energy consumption while improving the living standard of people, the energy consumption of the refrigerating station system accounts for 60% -80% of the total energy consumption of the air conditioning system, and the energy efficiency model fitting of the refrigerating station is related to the energy consumption calculation and the follow-up energy saving optimization control of the whole system, so that the research on the energy efficiency model fitting of the refrigerating station system has important significance on the air conditioning system.
At present, the fitting method of the refrigeration station energy efficiency model mainly comprises the following steps: 1) Statistical regression method: model fitting, such as linear regression, polynomial regression, or nonlinear regression, is performed using statistical regression methods by collecting and analyzing a large amount of experimental data; 2) The machine learning method comprises the following steps: fitting a refrigeration station energy efficiency model by training a model by using a machine learning algorithm such as a neural network, a support vector machine, a decision tree and the like; 3) The physical modeling method comprises the following steps: based on the physical principle and energy balance equation of the refrigerating station, a mathematical model is established, and experimental data is utilized to perform parameter fitting and correction.
However, as the refrigerating station system has numerous devices and complex structures and has complex characteristics such as nonlinearity, large hysteresis, time variation, strong coupling and the like, difficulties are brought to mechanism modeling and energy efficiency model fitting, and aiming at the complex nonlinear model of the refrigerating station, the single fitting method has limited effect and cannot accurately capture the dynamic characteristics of the system.
Disclosure of Invention
The invention aims to provide a refrigeration station energy efficiency model fitting method and device so as to improve the accuracy of a refrigeration station fitting model.
The invention adopts the following technical scheme: a refrigerating station energy efficiency model fitting method comprises the following steps:
acquiring a water chilling unit operation power model, a freeze pump operation power model, a cooling tower fan operation power model and refrigerating capacity of the water chilling unit; the water chiller running power model is obtained by fitting a support vector machine regression algorithm with multi-core learning, and the fitting data set comprises refrigerating capacity, outdoor wet bulb temperature, water supply temperature and water chiller energy efficiency;
constructing a total running power model of the refrigeration station for the water chilling unit running power model, the freezing pump running power model, the cooling pump running power model and the cooling tower fan running power model;
and establishing a refrigerating station energy efficiency model according to the refrigerating capacity and the running total power model.
Further, the fitting of the running power model of the water chilling unit through a support vector machine regression algorithm with multi-core learning comprises the following steps:
constructing an energy efficiency model of the water chilling unit;
solving parameters of a chiller energy efficiency model by adopting a support vector machine regression algorithm based on the fitting data set; selecting a sigmoid kernel function and a Gaussian radial basis kernel function during solving;
and constructing a water chilling unit operation power model according to the solved water chilling unit energy efficiency model.
Further, the running power model of the water chilling unit is as follows:
P set ＝Q set /COP set ，
wherein P is set For the running power of the water chilling unit, Q set For refrigerating capacity, COP set Is the energy efficiency of the water chilling unit;
the energy efficiency of the water chilling unit is obtained through a water chilling unit energy efficiency model, and the water chilling unit energy efficiency model is as follows:
COP set (x i )＝ω·φ(x i )+b，
wherein, COP set (x i ) Representing an input value x i Corresponding water chilling unit energyEffect, x i Comprises refrigerating capacity, outdoor wet bulb temperature and water supply temperature, wherein omega is a weight vector, b is a bias constant, phi (x) i ) As a kernel function, the kernel function includes a sigmoid kernel function phi 1 And a Gaussian radial basis function phi 2 。
Further, the cryopump operating power model is:
wherein P is pumpf For cryopump operating power, gamma f For the volume weight of the fluid in the cryopump, V pumpf For refrigerating pump flow, H f For the head of the refrigeration pump, eta pumpf For cryopump efficiency, η pumpf,d For the transmission efficiency of the cryopump, eta pumpf,g For cryopump motor efficiency, η pumpf,f Is the frequency converter efficiency.
Further, the cooling pump operating power model is:
wherein P is pumpc To cool the pump operating power, gamma c To cool the volume weight of the fluid in the pump, V pumpc To cool the pump flow, H c To cool the pump head, eta pumpc For cooling pump efficiency, η pumpc,d For cooling pump transmission efficiency eta pumpc,g To cool the pump motor efficiency, η pumpc,f For cooling the pump inverter efficiency.
Further, the cooling tower fan operation power model is:
P tower ＝u 2 ·k tower ，
wherein P is tower For the operating power of the fan of the cooling tower, u 2 To fit parameters, k tower Is the rotation speed ratio of the cooling tower fan.
Further, the calculating mode of the fan rotation speed ratio of the cooling tower is as follows:
k tower ＝V a /u 1 ，
wherein V is a For air flow, u 1 Is a fitting parameter.
Further, the air flow is obtained by a cooling tower simplified model, which is:
wherein Q is ch D, for cooling the heat of the cooling tower 1 ，d 2 And d 3 Are all fitting parameters, V w For cooling water flow, T cin The water inlet temperature of the cooling water is; t (T) w Is the outdoor wet bulb temperature.
Another technical scheme of the invention is as follows: a refrigerating station energy efficiency model fitting device comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the method.
The beneficial effects of the invention are as follows: the invention combines the data driving and physical modeling methods, gives full play to the respective advantages of the machine learning and physical modeling methods, and the support vector machine regression algorithm of multi-core learning obtains better regression effect by combining the advantages of different kernel functions, improves the fitting precision and accuracy of the energy efficiency model of the refrigerating station, reduces the consumption of calculation resources, ensures that the fitting method is more practical and feasible, and lays the foundation of the follow-up energy conservation and the optimization control of the refrigerating station.
Drawings
FIG. 1 is a model fitting flow chart of a cold water unit in an embodiment of the invention;
fig. 2 is a schematic diagram of a method for calculating comprehensive energy efficiency of a refrigeration station according to an embodiment of the present invention.
Detailed Description
The invention will be described in detail below with reference to the drawings and the detailed description.
The invention discovers that the fitting accuracy and stability of the energy efficiency model of the refrigeration station can be improved by combining a data driving and physical modeling method, and the energy saving potential of the refrigeration station is fully excavated. The energy consumption equipment of the refrigerating station system mainly comprises a water chilling unit, a refrigerating pump, a cooling pump and a cooling tower fan, wherein the energy consumption of the water chilling unit accounts for 55% of the total energy consumption of the system, the energy consumption of the refrigerating pump and the cooling pump accounts for 38%, the energy consumption of the cooling tower fan accounts for 7%, and the energy efficiency of each equipment is related to each other.
The refrigerating station system mainly comprises a water chilling unit, a chilled water loop and a cooling water loop, wherein the water chilling unit is a core component and mainly comprises an evaporator, a compressor, a condenser and an expansion valve. The water chilling unit is mainly responsible for preparing cold energy, and the working principle is a circulation process that the refrigerant continuously absorbs heat and releases heat.
Firstly, absorbing heat of chilled water backwater in an evaporator by liquid refrigerant to be changed into a gaseous state, and then compressing the gaseous state into high-temperature and high-pressure gas through a compressor; then, the high-temperature and high-pressure gas transfers heat to cooling water in a condenser through heat exchange, the cooling water brings the heat to a cooling tower to be discharged, and the gaseous refrigerant becomes liquid after the temperature is reduced; then the low-temperature high-pressure liquid refrigerant flows through the expansion valve under the pushing of the system, and the liquid refrigerant changed into low-temperature low-pressure liquid refrigerant is sent into the evaporator again to enter the next circulation.
The freezing pump and the freezing water pipeline form a freezing water loop together. The refrigerating water is firstly subjected to heat exchange with the refrigerant at the evaporator, is cooled, is pressurized by a refrigerating pump and is sent into a refrigerating water pipeline, then flows to an air treatment unit at the tail end of the air conditioner, is subjected to heat exchange with air entering the room, and takes away air heat. The air after the cooling treatment enters the room to achieve the purpose of reducing the indoor temperature; at the same time, the temperature of the chilled water is increased due to the absorption of the air heat, the warmed chilled water enters the evaporator again to exchange heat with the refrigerant, and the process is repeated.
The cooling pump, the cooling water pipeline and the cooling tower form a cooling water loop together. During operation of the system, the cooling water absorbs heat released by the refrigerant at the condenser, thereby increasing the temperature. Then, the cooling pump presses the warmed cooling water into the cooling tower to exchange heat with the external environment. Finally, the cooled cooling water returns to the water chilling unit to enter the next circulation.
The invention discloses a refrigeration station energy efficiency model fitting method, which is shown in fig. 1 and comprises the following steps: acquiring a water chilling unit operation power model, a freeze pump operation power model, a cooling tower fan operation power model and refrigerating capacity of the water chilling unit; the water chiller running power model is obtained by fitting a support vector machine regression algorithm with multi-core learning, and the fitting data set comprises refrigerating capacity, outdoor wet bulb temperature, water supply temperature and water chiller energy efficiency; constructing a total running power model of the refrigeration station for the water chilling unit running power model, the freezing pump running power model, the cooling pump running power model and the cooling tower fan running power model; and establishing a refrigerating station energy efficiency model according to the refrigerating capacity and the running total power model.
The invention combines the data driving and physical modeling methods, gives full play to the respective advantages of the machine learning and physical modeling methods, and the support vector machine regression algorithm of multi-core learning obtains better regression effect by combining the advantages of different kernel functions, improves the fitting precision and accuracy of the energy efficiency model of the refrigerating station, reduces the consumption of calculation resources, ensures that the fitting method is more practical and feasible, and lays the foundation of the follow-up energy conservation and the optimization control of the refrigerating station.
In the embodiment of the invention, the refrigeration station energy efficiency model is specifically as follows:
wherein, COP system For the system energy efficiency ratio (i.e. the integrated energy efficiency of the refrigerating station), Q set The refrigerating capacity of the water chilling unit is unit kW, P total The unit kW is the sum of the operating power of each device of the refrigeration station.
From the above analysis, it can be seen that:
P total ＝P set +P pumpf +P pumpc +P tower (2)
wherein P is set For the running power of the water chilling unit, P pumpf To the operating power of the cryopump, P pumpc To cool the pump operating power, P tower The unit is kW for the cooling tower fan operating power.
In one embodiment, as shown in fig. 2, the fitting of the chiller running power model by the support vector machine regression algorithm with multi-core learning includes: constructing an energy efficiency model of the water chilling unit; solving parameters of a chiller energy efficiency model by adopting a support vector machine regression algorithm based on the fitting data set; selecting a sigmoid kernel function and a Gaussian radial basis kernel function during solving; and constructing a water chilling unit operation power model according to the solved water chilling unit energy efficiency model.
For model fitting of the chiller, a support vector machine regression algorithm of multi-core learning is adopted in the embodiment, and support vector regression (Support Vector Regression, abbreviated as SVR) is a regression method based on a support vector machine. Unlike traditional regression methods, SVR focuses on finding a boundary such that most training samples are inside the boundary and the distance of the boundary to the training samples is minimal.
In this embodiment, firstly, an influence factor analysis is performed to obtain the COP of the energy efficiency of the water chiller set After analysis of the influencing factors, the influencing factors are mainly the cooling load Q set (namely the refrigerating capacity of the water chilling unit), and the outdoor wet bulb temperature T w And water supply temperature T eo The method comprises the steps of carrying out a first treatment on the surface of the And then data acquisition and processing are carried out, data acquired by the operation of the refrigerating station are stored and processed, abnormal data are removed, missing values are interpolated, and preprocessing operations such as feature scaling and standardization are carried out on a given training data set so as to ensure the scale consistency of each feature.
A model is then defined to fit the data by constructing a hyperplane in the feature space, the hyperplane being determined by the support vector, wherein the hyperplane can be represented as a linear function or a nonlinear function.
Then, an objective function is constructed, wherein the objective function consists of two parts, one part is used for ensuring the constraint condition of the training sample in the hyperplane, and the other part is used for minimizing the distance between the hyperplane and the training sample (x, y), so that an optimized problem can be obtained, and the optimal hyperplane can be found by solving the problem.
And finally solving the optimization problem, solving the optimization problem by using a quadratic programming method in the convex optimization theory, and obtaining an optimal solution by solving a dual problem to obtain fitting parameters.
The idea of the support vector machine regression algorithm is that a kernel function phi is used for mapping a data set to a high-dimensional feature space H, and linear regression is performed in the space, so that the original nonlinear problem is skillfully converted into the linear problem in the high-dimensional space, and the effect of linear regression in the original space is achieved. The specific functional form (i.e., chiller energy efficiency model) can be expressed as:
COP set (x i )＝ω·φ(x i )+b (3)
wherein, COP set (x i ) Representing an input value x i Energy efficiency (output quantity) of corresponding water chilling unit, x i Comprises refrigerating capacity, outdoor wet bulb temperature and water supply temperature, wherein omega is a weight vector, b is a bias constant, phi (x) i ) As a kernel function, the kernel function includes a sigmoid kernel function phi 1 And a Gaussian radial basis function phi 2 。
Thus, the linear regression in the high-dimensional feature space corresponds to the nonlinear regression in the low-dimensional space, and the dot product calculation of the high-dimensional space ω and Φ is avoided, ω and b in equation (3) can be estimated by the minimization equation (4).
Wherein the 1 st item (ω·ω) represents the function COP set (x i ) Is complex; item 2 represents experience risk, where |y i -COP set (x i )| ε ＝max{0,|y i -f(x i ) The use of | -epsilon } as a insensitive loss function is that the decision function can be represented by sparse points, epsilon being the maximum error allowed by regression,epsilon controls the number of support vectors and generalization capability, the larger the value is, the fewer the support vectors are, C is a positive constant, and the compromise degree between the complexity of the function class and the average loss on the training set is reflected. By utilizing the dual principle, a Lagrangian function and a kernel function are simultaneously introduced, the minimization formula (4) is converted into an optimization problem, and the offset b is solved according to the Kuhn-Tucker theorem.
In the embodiment of the invention, the regression algorithm of the support vector machine is improved, multi-core learning is added, and the advantages of different kernel functions are combined to obtain better regression effect, so that two kernel functions sigmoid kernel functions phi are selected 1 And a Gaussian radial basis function phi 2 ：
φ 1 (x 1 ,x 2 )＝tanh(g 1 *x 1 *x 2 +coef) (5)
φ 2 (x 1 ,x 2 )＝exp(-g 2 *||x 1 -x 2 || 2 ) (6)
Wherein x is 1 And x 2 Respectively different input samples x i ；g 1 ，g 2 Coef is a parameter of the kernel function, respectively.
Building the regression algorithm model of the multi-core learning support vector machine, and then taking the cold load Q as a model set Outdoor wet bulb temperature T w And water supply temperature T eo As input, the energy efficiency COP of the water chilling unit set Training the model to obtain trained parameters, namely, energy efficiency COP of the water chilling unit through a multi-core learning support vector machine regression algorithm set Fitting calculation is performed.
Furthermore, the running power model of the water chilling unit can be obtained as follows:
P set ＝Q set /COP set (7)
Q ch ＝P set *(1+COP set ) (8)
wherein P is set For the running power of the water chilling unit, Q set For refrigerating capacity, COP set Is the energy efficiency of the water chilling unit.
In one embodiment, the cryopump operating power model is:
wherein P is pumpf For cryopump operating power, gamma f For the volume weight of the fluid in the cryopump, V pumpf For refrigerating pump flow, H f For the head of the refrigeration pump, eta pumpf For cryopump efficiency, η pumpf,d For the transmission efficiency of the cryopump, eta pumpf,g For cryopump motor efficiency, η pumpf,f Is the frequency converter efficiency.
For the cryopump, a physical mechanism modeling method is adopted in the embodiment, a mathematical model is firstly established, then data are collected and processed, and parameter fitting is carried out according to the data.
Flow V of cryopump pumpf And (3) calculating:
wherein c is the specific heat capacity of water, which in this example is 4.2; dT is the chilled water temperature differential, taken as 7 in this example.
The curve formula of the chilled water pipeline, the H-V curve of the chilled pump and the running power formula of the chilled pump are respectively as follows:
wherein H is f A pump head for the refrigeration pump; s is S f The impedance of the pipe network of the refrigeration system; a, a pumpf 、b pumpf And c pumpf Are fitting parameters; k (k) pumpf For the rotation speed ratio of the cryopump, eta pumpf For cryopump efficiency, η pumpf,d For transmission efficiency eta pumpf,g For motor efficiency, eta pumpf,f G is the efficiency of the frequency converter f1 And g f2 Are fitting parameters; f (f) 0 ，f 1 ，f 2 And f 3 Are all fitting parameters, gamma f KN/m is the volume weight of the fluid in the cryopump 3 The water was taken as fluid 9.8.
For the cooling pump and the cooling tower, a physical mechanism modeling method is also adopted, a mathematical model is firstly established, then data are collected and processed, and parameter fitting is carried out according to the data.
The model in the embodiment of the invention needs to model by regarding the cooling pump and the cooling tower as a whole, and then calculates the heat exchange quantity of the water chilling unit as Q ch And when the total operation power of the cooling tower and the cooling pump is the minimum value, the total operation power at the moment is taken as the operation power of the whole cooling system.
Specifically, the cooling pump operation power model is:
wherein P is pumpc To cool the pump operating power, gamma c To cool the volume weight of the fluid in the pump, V pumpc To cool the pump flow, H c To cool the pump head, eta pumpc For cooling pump efficiency, η pumpc,d For cooling pump transmission efficiency eta pumpc,g To cool the pump motor efficiency, η pumpc,f For cooling the pump inverter efficiency.
The curve formula of the cooling water pipeline, the H-V curve of the cooling pump and the operation power formula of the cooling pump are respectively as follows:
wherein S is c For the impedance of the cooling system pipe network, a pumpc 、b pumpc And c pumpc To fit parameters, k pumpc For cooling pump speed ratio, eta pumpc G for cooling pump efficiency c1 And g c2 Respectively fitting parameters, c 0 ，c 1 ，c 2 And c 3 Fitting parameters; gamma ray c KN/m is the volume weight of the fluid 3 The water was taken as fluid 9.8.
For the cooling pump rotation speed ratio k pumpc In general, the present embodiment takes the range of 0.5 to 1, which is related to the adjustable range of the frequency converter, so k is respectively pumpc =0.5 and k pumpc =1 substituted into formulas (16) and (17) to calculate the corresponding cooling pump flow V pumpc1 And V pumpc2 The flow value range of the cooling pump is obtained.
If n cooling pumps are provided, the flow rate value range of the n cooling pumps needs to be calculated. The sum of all cooling pump flows is equal to the cooling water flow.
The air flow is obtained by a simplified cooling tower model, which is:
wherein Q is ch D, for cooling the heat of the cooling tower 1 ，d 2 And d 3 Are all fitting parameters, V w For cooling water flow, T cin The water inlet temperature of the cooling water is; t (T) w Is the outdoor wet bulb temperature. In the embodiment of the invention, the inlet water temperature of the cooling water is 1 to 5 ℃ higher than the outdoor wet bulb temperature.
If there are m cooling towers, the operation power of each corresponding cooling tower when 1 to m cooling towers are started is calculated respectively.
The calculation mode of the cooling tower fan rotation speed ratio is as follows:
k tower ＝V a /u 1 (21)
wherein V is a For air flow, u 1 Is a fitting parameter.
The cooling tower fan operating power model is thus:
P tower ＝u 2 ·k tower (22)
wherein P is tower For the operating power of the fan of the cooling tower, u 2 To fit parameters, k tower Is the rotation speed ratio of the cooling tower fan.
Q is calculated from equation (20) ch ，T w Ratio T w T of 1 to 5 cin And cooling pump flow V pumpc1 To V pumpc2 All air flow under the air flow, then calculating to obtain the corresponding operating power of the cooling tower under each air flow according to a formula, and finally calculating and determining Q ch ，T w ，T cin The minimum total running power of the cooling pump and the cooling tower is recorded, and the flow V of the corresponding cooling pump is recorded minc And the rotation speed ratio k of the cooling tower fan tower 。
The invention also discloses a refrigeration station energy efficiency model fitting device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the method.
The present invention may be implemented in whole or in part by a computer program which, when executed by a processor, performs the steps of the various method embodiments described above, and which may be embodied in a computer readable storage medium. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a storage device, a recording medium, computer Memory, read-Only Memory (ROM), random access Memory (RAM, random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media. Such as a U-disk, removable hard disk, magnetic or optical disk, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Claims (9)
1. The refrigerating station energy efficiency model fitting method is characterized by comprising the following steps of:
acquiring a water chilling unit operation power model, a freeze pump operation power model, a cooling tower fan operation power model and refrigerating capacity of the water chilling unit; the water chiller running power model is obtained through fitting by a support vector machine regression algorithm with multi-core learning, and a fitting data set comprises the refrigerating capacity, the outdoor wet bulb temperature, the water supply temperature and the water chiller energy efficiency;
constructing a total running power model of the refrigeration station for the water chilling unit running power model, the freezing pump running power model, the cooling pump running power model and the cooling tower fan running power model;
and establishing a refrigerating station energy efficiency model according to the refrigerating capacity and the running total power model.
2. The method of fitting a refrigeration station energy efficiency model according to claim 1, wherein the fitting of the chiller running power model by a support vector machine regression algorithm with multi-kernel learning comprises:
constructing an energy efficiency model of the water chilling unit;
solving parameters of the water chiller energy efficiency model by adopting a support vector machine regression algorithm based on the fitting data set; selecting a sigmoid kernel function and a Gaussian radial basis kernel function during solving;
and constructing a water chilling unit operation power model according to the solved water chilling unit energy efficiency model.
3. The method for fitting a refrigeration station energy efficiency model as set forth in claim 2, wherein said chiller operation power model is:
P set ＝Q set /COP set ，
wherein P is set For the running power of the water chilling unit, Q set For the refrigerating capacity, COP set Is the energy efficiency of the water chilling unit;
the energy efficiency of the water chilling unit is obtained through a water chilling unit energy efficiency model, and the water chilling unit energy efficiency model is as follows:
COP set (x i )＝ω·φ(x i )+b，
wherein, COP set (x i ) Representing an input value x i Energy efficiency, x of corresponding water chilling unit i Comprises refrigerating capacity, outdoor wet bulb temperature and water supply temperature, wherein omega is a weight vector, b is a bias constant, phi (x) i ) Is a kernel function comprising a sigmoid kernel function phi 1 And a Gaussian radial basis function phi 2 。
4. A method of modeling energy efficiency of a refrigeration station as claimed in claim 2 or 3 wherein said refrigeration pump operating power model is:
wherein P is pumpf Is coldOperating power of freeze pump, gamma f For the volume weight of the fluid in the cryopump, V pumpf For refrigerating pump flow, H f For the head of the refrigeration pump, eta pumpf For cryopump efficiency, η pumpf,d For the transmission efficiency of the cryopump, eta pumpf,g For cryopump motor efficiency, η pumpf,f Is the frequency converter efficiency.
5. The method of modeling energy efficiency of a refrigeration station as claimed in claim 4, wherein said cooling pump operating power model is:
wherein P is pumpc To cool the pump operating power, gamma c To cool the volume weight of the fluid in the pump, V pumpf To cool the pump flow, H c To cool the pump head, eta pumpc For cooling pump efficiency, η pumpc,d For cooling pump transmission efficiency eta pumpc,g To cool the pump motor efficiency, η pumpc,f For cooling the pump inverter efficiency.
6. The method for fitting a refrigeration station energy efficiency model as set forth in claim 5, wherein said cooling tower fan operating power model is:
P tower ＝u 2 ·k tower ，
wherein P is tower For the operating power of the fan of the cooling tower, u 2 To fit parameters, k tower Is the rotation speed ratio of the cooling tower fan.
7. The method for fitting a refrigeration station energy efficiency model as set forth in claim 6, wherein the speed ratio of the cooling tower fan is calculated by:
k tower ＝V a /u 1 ，
wherein V is a For air flow, u 1 Is a fitting parameter.
8. A method of modeling energy efficiency of a refrigeration station as defined in claim 7 wherein said air flow is obtained by a simplified model of a cooling tower, said simplified model of a cooling tower being:
wherein Q is ch D, for cooling the heat of the cooling tower 1 ，d 2 And d 3 Are all fitting parameters, V w For cooling water flow, T cin The water inlet temperature of the cooling water is; t (T) w Is the outdoor wet bulb temperature.
9. A refrigeration station energy efficiency model fitting device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 8 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310936790.3A CN116956734A (en) | 2023-07-27 | 2023-07-27 | Refrigeration station energy efficiency model fitting method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310936790.3A CN116956734A (en) | 2023-07-27 | 2023-07-27 | Refrigeration station energy efficiency model fitting method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116956734A true CN116956734A (en) | 2023-10-27 |
Family
ID=88454433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310936790.3A Pending CN116956734A (en) | 2023-07-27 | 2023-07-27 | Refrigeration station energy efficiency model fitting method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116956734A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118258098A (en) * | 2024-05-29 | 2024-06-28 | 深圳市天元维视实业有限公司 | Method, device, terminal and medium for constructing mathematical model of central air conditioning system |
-
2023
- 2023-07-27 CN CN202310936790.3A patent/CN116956734A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118258098A (en) * | 2024-05-29 | 2024-06-28 | 深圳市天元维视实业有限公司 | Method, device, terminal and medium for constructing mathematical model of central air conditioning system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105737426B (en) | A kind of CO2Compressor capacity matching method between Trans-critical cycle overlapping heat pump and its level | |
| CN109855238B (en) | Central air conditioner modeling and energy efficiency optimization method and device | |
| CN114484731B (en) | Central air conditioner fault diagnosis method and device based on stacking fusion algorithm | |
| CN113326651B (en) | Refrigerating station load and energy efficiency ratio dynamic modeling method based on T-S fuzzy model | |
| CN116956734A (en) | Refrigeration station energy efficiency model fitting method and device | |
| CN109186127B (en) | Global optimization control method for ground source heat pump | |
| CN106524410A (en) | Diagnosis method for actual efficiency of central air conditioner cooling water unit | |
| CN109543221B (en) | On-site fault diagnosis method for air conditioner water chilling unit | |
| CN102914108B (en) | Apparatus and method for evaluating performance of centrifugal chiller | |
| CN110631212B (en) | Energy-saving control method for central air-conditioning cooling water system | |
| CN109063255A (en) | A kind of energy-saving control method, electronic equipment, storage medium, apparatus and system | |
| CN106766450A (en) | Refrigeration heat pump system least energy consumption optimal control device and control method | |
| CN111898814B (en) | Central air conditioner energy consumption prediction method and device | |
| CN109000949A (en) | Water cooler appraisal procedure and power-economizing method based on water cooler thermodynamical model | |
| CN109000948A (en) | The more water chilling unit energy-saving space appraisal procedures based on cooling-water machine thermodynamical model | |
| CN116538645A (en) | Energy efficiency determining method for refrigeration machine room | |
| CN112747418A (en) | Air conditioner and cloud server | |
| CN117109158A (en) | Energy efficiency optimization method and device for air conditioning system | |
| CN113357842B (en) | CO (carbon monoxide) 2 Transcritical parallel compression refrigeration system and control method | |
| CN116792913A (en) | Parameter optimization method and device for refrigeration system | |
| CN109959097A (en) | A kind of centralization cold source cooling cycle system | |
| CN112728737A (en) | Air conditioner and cloud server | |
| CN112303819A (en) | Air conditioner and control method | |
| CN112503789B (en) | Intermediate pressure control method for cascade refrigeration system | |
| CN117928052B (en) | Energy-saving control method and system for central air conditioner |
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 |