CN114370696B - D-S evidence theory-based central air conditioner cooling tower water outlet temperature control method - Google Patents
D-S evidence theory-based central air conditioner cooling tower water outlet temperature control method Download PDFInfo
- Publication number
- CN114370696B CN114370696B CN202111614353.7A CN202111614353A CN114370696B CN 114370696 B CN114370696 B CN 114370696B CN 202111614353 A CN202111614353 A CN 202111614353A CN 114370696 B CN114370696 B CN 114370696B
- Authority
- CN
- China
- Prior art keywords
- cooling tower
- water
- cooling
- temperature
- outlet temperature
- 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
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
- F24F11/72—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure
- F24F11/74—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling air flow rate or air velocity
- F24F11/77—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling air flow rate or air velocity by controlling the speed of ventilators
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
- F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
- F24F11/83—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling the supply of heat-exchange fluids to heat-exchangers
- F24F11/84—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling the supply of heat-exchange fluids to heat-exchangers using valves
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
- F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
- F24F11/83—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling the supply of heat-exchange fluids to heat-exchangers
- F24F11/85—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling the supply of heat-exchange fluids to heat-exchangers using variable-flow pumps
-
- 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
Abstract
The invention discloses a method for controlling the outlet water temperature of a central air conditioner cooling tower based on a D-S evidence theory, which comprises the following steps: collecting different types of sensor parameters in the running process of a central air conditioning system, and taking the sensor parameters as original sample data reflecting the water outlet temperature of a cooling tower; preprocessing the original sample data, analyzing principal components and performing correlation analysis to obtain an input data set, and inputting the input data set into each intelligent prediction algorithm for training to obtain a plurality of corresponding cooling tower water outlet temperature prediction models; carrying out weight extraction and fusion on prediction results of the plurality of cooling tower water outlet temperature prediction models by adopting a D-S evidence theory to obtain a final cooling tower water outlet temperature prediction value; and comparing the predicted value of the water outlet temperature of the cooling tower with a set water outlet temperature value of the cooling tower, if the predicted value of the water outlet temperature of the cooling tower is inconsistent with the set water outlet temperature value of the cooling tower, taking the energy consumption of a cooling water system as an objective function, setting constraint conditions, and solving by adopting an intelligent optimizing algorithm to obtain the operation frequency combination of the cooling water pump and the cooling tower fan with optimal energy consumption so as to realize the control of the temperature.
Description
Technical Field
The invention belongs to the technical field of central air conditioners, and particularly relates to a method for controlling the outlet water temperature of a cooling tower of a central air conditioner based on a D-S evidence theory.
Background
In the development process of urban mass, the number and the mass of large public buildings are obviously increased along with the expansion of the mass of the urban mass, wherein the two major trends of building electrification which is rapidly developed and building intellectualization which is gradually developed are widely focused in the society. Because of the large-scale public refrigeration demands, the central air conditioning system and the automatic control system thereof are increasingly large in scale, and the equipment types and the quantity are increasingly large, so that the complexity of the system is higher and higher. Cooling towers are very popular water resource recycling devices, and the main function of the cooling towers is to exchange heat between cooling water containing waste heat and air in the towers, so that the water temperature is reduced to a required temperature for recycling. The cooling tower is used as an important radiating component of equipment such as a central air conditioning system and the like, and the water outlet temperature of the cooling tower can directly influence the operation performance of the water chilling unit, so that the water outlet temperature of the cooling tower is closely related to the overall operation performance of the central air conditioning system of the water chilling unit.
The cooling water system is a main functional part in the building air conditioning system. The operation energy consumption of the cooling water system is considerable in the energy consumption of the whole air conditioning system. In most cooling water systems, a cooling tower is used for system heat rejection purposes. In this type of cooling water system, the water inlet temperature (cooling tower water outlet temperature) of the condenser is adjusted for a specific load, the number of cooling towers running and the rotational speed of the fan are required to be changed, and the number and frequency of cooling water pumps running are required to be changed.
At present, a single algorithm model is generally adopted for predicting the outlet water temperature of the cooling tower, the prediction accuracy is low, and in order to ensure that the outlet water temperature of the cooling tower reaches the standard, how to control the outlet water temperature of the cooling tower, an optimal combination strategy between the cooling tower and a cooling water pump is found, so that the minimum energy consumption of a cooling water system is a problem which needs to be solved at present.
Based on the technical problems, a novel method for controlling the outlet water temperature of the central air conditioner cooling tower based on the D-S evidence theory needs to be designed.
Disclosure of Invention
The invention aims to provide a D-S evidence theory-based central air conditioner cooling tower water outlet temperature control method, which adopts the D-S evidence theory to establish a plurality of cooling tower water outlet temperature prediction models and perform model fusion, effectively improves model prediction accuracy, takes the energy consumption of a cooling water system as an objective function, adopts an intelligent optimizing algorithm to solve and obtain the operation frequency combination of a cooling water pump and a cooling tower fan with optimal energy consumption, and realizes control of the cooling tower water outlet temperature.
In order to solve the technical problems, the invention provides a method for controlling the outlet water temperature of a central air conditioner cooling tower based on a D-S evidence theory, which comprises the following steps:
S1, establishing a digital twin model of a cooling tower, a cooling water pump and a water chiller in a central air conditioning system by adopting a mechanism modeling and data identification method;
s2, collecting different types of sensor parameters in the running process of the central air conditioning system, and taking the sensor parameters as original sample data reflecting the water outlet temperature of the cooling tower; the raw sample data includes at least: the water inlet temperature of the cooling tower, the water inlet flow of the cooling tower, the air inlet quantity of the cooling tower, the air wet bulb temperature, the water-air mass ratio and the water outlet temperature of the cooling tower;
s3, preprocessing the original sample data, analyzing principal components and performing correlation analysis to obtain an input data set, and inputting the input data set into each intelligent prediction algorithm for training to obtain cooling tower water outlet temperature prediction models corresponding to the intelligent prediction algorithms;
s4, carrying out weight extraction and fusion on prediction results of the cooling tower water outlet temperature prediction models by adopting a D-S evidence theory to obtain a final cooling tower water outlet temperature prediction value;
and S5, comparing the predicted value of the water outlet temperature of the cooling tower with a set water outlet temperature value of the cooling tower, if the predicted value of the water outlet temperature of the cooling tower is inconsistent with the set water outlet temperature value of the cooling tower, setting corresponding constraint conditions by taking the energy consumption of a cooling water system as an objective function, solving and obtaining the operation frequency combination of a cooling water pump and a cooling tower fan with optimal energy consumption by adopting an intelligent optimizing algorithm, and performing variable frequency operation by adjusting the cooling water pump and the cooling tower fan to enable the water outlet temperature of the cooling tower to reach a set value so as to realize control of the water outlet temperature of the cooling tower.
Further, in the step S1, a digital twin model of a cooling tower, a cooling water pump and a water chiller in a central air conditioning system is established by adopting a mechanism modeling and data identification method, and the method specifically comprises the following steps:
constructing a physical model, a logical model and a simulation model of a water chilling unit, wherein the water chilling unit is used for providing chilled water with a certain temperature for the tail end of the physical model of the water chilling unit, and comprises a compressor, an evaporator, a condenser and a throttle valve;
constructing a physical model, a logical model and a simulation model of the cooling tower;
constructing a physical model, a logical model and a simulation model of the cooling water pump; wherein, the liquid crystal display device comprises a liquid crystal display device,
the construction of the logic model comprises the following steps: establishing a controllable closed-loop logic model according to the logic mechanism relation among all physical entities of the central air conditioning system, and mapping the physical model to the logic model;
the construction of the simulation model comprises the following steps: constructing a central air conditioning system simulation model based on the collected operation data, state data and physical attribute data of the central air conditioning system;
carrying out virtual-real fusion on the physical model, the logic model and the simulation model, and constructing a system-level digital twin model of physical entities of the cooling tower, the cooling water pump and the water chiller in a virtual space;
And accessing the multi-working-condition real-time operation data of the cooling tower, the cooling water pump and the water chilling unit into the system-level digital twin model, and carrying out self-adaptive identification correction on the simulation result of the system-level digital twin model by adopting a reverse identification method to obtain the digital twin model of the cooling tower, the cooling water pump and the water chilling unit in the central air conditioning system after identification correction.
Further, the simulation model establishment of the water chilling unit comprises the following steps:
neglecting the suction and exhaust pressure loss of the compressor and neglecting the heat exchange between the compressor and the environment, and establishing a compressor model to be expressed as:
wherein m is r Is the refrigerant mass flow; v (V) th Gas delivery capacity is a mechanism of compression; v 1 The specific volume of suction gas for the compressor; ζ is the gas transmission coefficient; p (P) ths Theoretical power consumption of the isentropic compression process of the compressor; p (P) i The power consumption of the actual compression process of the compressor is the indicated power; p (P) el The electric power input for the actual compression process of the compressor, namely the power measured by a power meter; k is an isentropic compression index; p (P) e Is the evaporating pressure, i.e. the compressor suction pressure; p (P) k Is the condensing pressure, i.e., compressor discharge pressure; η (eta) i An indicated efficiency for the compressor; η (eta) el Is the electrical efficiency of the compressor; h is a 2 Enthalpy for the compressor outlet refrigerant; h is a 1 Enthalpy for the compressor inlet refrigerant;
the simulation model establishment of the condenser comprises the following steps:
neglecting heat exchange between the condenser and the outside, regarding the flow of the refrigerant and the cooling water as one-dimensional uniform flow, and obtaining the heat exchange process in the condenser is expressed as:
Q c =m w,c c p,w (t wo,c -t wi,c )=m r (h ri,c -h ro,c );
Q 1,c =K 1,c F 1,c Δt 1,c ;
Q 2,c =K 2,c F 2,c Δt 2,c ;
Q 3,c =K 3,c F 3,c Δt 3,c ;
wherein Q is c The total heat exchange amount of the condenser; m is m w,c Is the flow of cooling water; c p,w The constant pressure specific heat of water; t is t wi,c The inlet temperature of cooling water; t is t wo,c Is the cooling water outlet temperature; t is t ri,c Is the refrigerant inlet temperature; t is t ro,c Is the refrigerant outlet temperature; t is t r,c Is the condensation temperature; m is m r Is the refrigerant flow; h is a ri,c Is the enthalpy of the condenser inlet refrigerant; h is a ro,c Is the outlet enthalpy value of the condenser; q (Q) 1,c 、Q 2,c 、Q 3,c The heat exchange amount of the condenser superheat zone, the two-phase zone and the supercooling zone is respectively; f (F) 1,c 、F 2,c 、F 3,c The heat exchange areas of the condenser superheat zone, the two-phase zone and the supercooling zone are respectively; Δt (delta t) 1,c 、Δt 2,c 、Δt 3,c The heat exchange temperature difference is respectively the heat exchange temperature difference of the condenser superheat zone, the two-phase zone and the supercooling zone; k (K) 1,c 、K 2,c 、K 3,c The heat transfer coefficients of the condenser superheat zone, the two-phase zone and the supercooling zone are respectively;
the simulation model establishment of the evaporator comprises the following steps:
neglecting heat exchange between the evaporator and the outside, regarding the flow of the refrigerant and the chilled water as one-dimensional uniform flow, and obtaining the heat exchange process in the evaporator is expressed as:
Q e =m w,e c p,w (t wi,e -t wo,e )=m r (1-x)(h ro,e -h ri,e );
Q 1,e =K 1,e F 1,e Δt 1,e ;
Q 2,e =K 2,e F 2,e Δt 2,e ;
wherein Q is e Heat exchange capacity for the evaporator; m is m w,e Is the flow of the chilled water; t is t wi,e Chilled water temperature for evaporator inlet; t is t wo,e Chilled water temperature for evaporator outlet; t is t w1,e Chilled water temperature for the inlet of the two-phase zone; h is a ri,e Is the evaporator inlet enthalpy; h is a ro,e Is the evaporator outlet enthalpy; x is the dryness of the refrigerant at the inlet of the evaporator; q (Q) 1,e Heat exchange amount for the overheat area of the evaporator; q (Q) 2,e Heat exchange capacity is carried out for the two-phase region of the evaporator; Δt (delta t) 1,e The heat exchange temperature difference is the superheat region of the evaporator; Δt (delta t) 2,e The heat exchange temperature difference is the two-phase area of the evaporator; t is t ro,e The suction temperature of the compressor, namely the outlet refrigerant temperature of the evaporator; t is t r,e Is the evaporation temperature;
the simulation model establishment of the throttle valve comprises the following steps:
the thermal expansion valve is formed by the pressure P of a temperature sensing medium in a temperature sensing bulb b Providing a valve opening force from the steam pressure P c And a spring force providing a valve closing force, the spring force being minimal when the valve is in a closed state, ΔP min The method comprises the steps of carrying out a first treatment on the surface of the Valve displacement y and P b 、P c 、ΔP min The relationship between them is expressed as: y=k (P b -P c -ΔP min ) The method comprises the steps of carrying out a first treatment on the surface of the k is the reciprocal of the spring rate;
the simulation model establishment of the cooling water pump comprises the following steps:
the rotation speed ratio f of the water pump is defined as the rotation speed n of the water pump motor and the rated motor rotation speed n 0 The ratio is expressed as:
the relationship between the pump lift, pump efficiency and pump flow and speed ratio is expressed as:
wherein H is pu Is the lift of the water pump; m is m w Is the mass flow of the water pump; η (eta) pu The efficiency of the water pump is achieved; h is a 01 、h 02 、h 03 、h 11 、h 12 、h 13 Fitting coefficients;
the simulation model establishment of the cooling tower comprises the following steps:
the total heat transfer rate of the cooling tower is expressed as: q=ε a m a (h a,w,i -h a,i );ε a Heat transfer rate for the air side; m is m a Is the mass flow of air; h is a a,w,i The enthalpy value of the humid air at the cooling water inlet; h is a a,i An enthalpy value for the humid air at the cooling tower air inlet;
the mass flow of water at the water outlet of the cooling tower is expressed as: m is m w,o =m w,i -m a (w a,o -w a,i )+m m ;m m The mass flow rate of the make-up water; w (w) a,o The air moisture content at the air outlet of the cooling tower; w (w) a,i The air humidity content at the air inlet of the cooling tower; m is m w,i Is the mass flow of the water inlet and the water outlet of the cooling tower.
Further, in the step S3, preprocessing, principal component analysis, and correlation analysis are performed on the raw sample data to obtain an input data set, which specifically includes:
preprocessing the original sample data, including: the method comprises the steps of missing value filling, repeated value deleting, normalization and wavelet noise filtering;
the method for performing data dimension reduction on the preprocessed data by adopting a principal component analysis method comprises the following steps: the preprocessed data are formed into an n-row m-column matrix X according to columns, each row of the matrix X is subjected to zero-mean, namely the mean value of the row is subtracted, and a covariance matrix is obtained; then, the eigenvalues and the corresponding eigenvectors of the covariance matrix are obtained, the eigenvectors are arranged into a matrix according to the corresponding eigenvalues from top to bottom, the first k rows are taken to form a matrix P, and Y=PX is the data after dimension reduction to k dimensions;
Calculating the correlation coefficient of the cooling tower water outlet temperature and other data by using the Pearson correlation coefficient R, wherein the calculation comprises the following steps: and calculating the correlation coefficient between two groups of different data, if the Pelson correlation coefficient value is larger than the coefficient threshold value, judging the data as data with high correlation with the control of the cooling tower water outlet temperature, and taking the data as an input data set of a cooling tower water outlet temperature prediction model.
Further, in the step S3, the input data set is input into each intelligent prediction algorithm to perform training, so as to obtain a cooling tower water outlet temperature prediction model corresponding to the plurality of intelligent prediction algorithms, which specifically includes:
inputting the input data set into each intelligent prediction algorithm for training to obtain a cooling tower water outlet temperature prediction model corresponding to each intelligent prediction algorithm; each intelligent prediction algorithm at least comprises: support vector machine algorithm, convolutional neural network algorithm, XGBoost algorithm, BP neural network algorithm and Bayesian network algorithm;
and respectively predicting the water outlet temperature of the cooling tower through the plurality of cooling tower water outlet temperature prediction models to obtain a prediction result P 1 、P 2 、P 3 ……P i And calculates the prediction result P i Error e from true value R i Expressed as:
Further, in the step S4, the weight extraction and fusion are performed on the prediction results of the plurality of cooling tower water outlet temperature prediction models by adopting a D-S evidence theory, so as to obtain a final cooling tower water outlet temperature prediction value, which specifically includes:
according to error e i Calculating the weight w of the fused sample i Expressed as:epsilon is the introduced coefficient;
let the predicted value of the cooling tower water outlet temperature predicted model be P i The corresponding weight is w i In the recognition frame Θ= { P 1 ,P 2 ,P 3 …P i Establishing a basic credibility allocation m, wherein the corresponding basic credibility value is expressed as: m is m j (P i )=w i The method comprises the steps of carrying out a first treatment on the surface of the j is the corresponding predicted date;
set Bel j For the confidence function corresponding to the confidence value, firstly 2 times of fusion are carried out on the confidence function, then 3 times of fusion are carried out on the 2 times of fusion result and the confidence function corresponding to the predicted value of the next day, and the like until the fusion is finished, and the result is expressed as:and simultaneously, the corresponding basic credibility value is expressed as: m is m c (P 1 )、m c (P 2 )、m c (P 3 )、……、m c (P i ) The basic credibility value is the weight fused with the water outlet temperature prediction model of the cooling tower on day c;
assume that the prediction results of the water outlet temperature prediction models of the cooling towers on the c days are respectively P 1 c 、……、P i c The final result of the fusion of the predicted data of the water outlet temperature of the cooling tower on day c is expressed as:
Further, in the step S5, with the energy consumption of the cooling water system as an objective function, a corresponding constraint condition is set, which specifically includes:
establishing an energy consumption objective function of a cooling water system:
minP total =min(P pump +P tower +P chiller ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein P is pump 、P tower 、P chiller The energy consumption of the cooling water pump, the cooling tower and the water chilling unit are respectively;
wherein, is the density of water; g is the local gravitational acceleration; h is the lift; g w Is the volume flow of the water flow; η (eta) p The efficiency of the water pump is achieved; η (eta) m The motor efficiency is; n is n f The frequency converter efficiency;
wherein, the number of variable frequency fans in one cooling tower; n is n i The actual rotating speed of the variable frequency fan; n is n o The rated rotation speed of the variable frequency fan is set; p (P) max The rated power of a variable-frequency fan is set;
wherein, the real-time load rate of the water chilling unit is,Q e for the real-time cold load of the water chilling unit, Q 0 Rated cold load for the water chilling unit; t (T) e 、T c The evaporation temperature and the condensation temperature of the water chilling unit are respectively;
setting constraint conditions:
cooling water pump frequency constraint:wherein (1)>Is the upper limit of the power consumption of the cooling water pump,Lower limit of power consumption of cooling water pump, F pump Is the actual value of the power consumption of the cooling water pump;
cooling tower fan frequency constraint:wherein (1)>Is the lower limit of the fan frequency of the cooling tower,Is the upper limit of the fan frequency of the cooling tower, F tower Is the actual value of the cooling tower fan frequency;
Cooling water inlet temperature constraint:wherein T is c in Is the water inlet temperature of cooling water, < >>Is the lower limit of the water inlet temperature of cooling water, < >>Is the upper limit of the water inlet temperature of the cooling water;
the number of cooling towers is restricted:wherein N is tower For the number of cooling towers, < > or >>Is the lower limit of the number of cooling towers to be operated, < >>Is the upper limit of the number of cooling towers;
and (3) constraining the number of cooling water pumps:wherein N is pump The number of the cooling water pumps is the number,The lower limit of the number of the cooling water pumps is->Is the upper limit of the number of the cooling water pumps.
Further, in the step S5, the operation frequency combination of the cooling water pump and the cooling tower fan with optimal energy consumption is obtained by solving by adopting an intelligent optimizing algorithm, which specifically includes:
initializing a firefly optimizing algorithm population: setting the population quantity of fireflies as M, the absorption coefficient of the medium to light as gamma and the initial attraction degree beta 0 ;
Calculating the fitness value of each firefly according to the position of the firefly, wherein the higher the fitness value is, the higher the firefly brightness is;
each firefly moves to all fireflies with higher brightness than the fireflies, and a moving distance calculation formula is expressed as follows:
s i ' is a position of firefly that is brighter than the ith individual; s is(s) i ,s j Is the solution space position of firefly i, j; r is the distance between the ith firefly and the jth firefly; zeta type toy i Is a random disturbance of firefly i; alpha is the step factor of the disturbance;
the individuals with the biggest brightness in the firefly population update the positions of the individuals;
calculating the adaptability value of a new position where the firefly flies to all other individuals with higher brightness than the firefly, if the position is better than the position before flying, the firefly flies to the new position, otherwise, the firefly stays in place;
if the algorithm reaches the maximum iteration times, outputting the searched optimal position of the firefly as a solution, otherwise, recalculating the fitness value of each firefly;
and obtaining the operation frequency combination of the cooling water pump and the cooling tower fan with optimal energy consumption based on the optimal firefly position.
Further, the intelligent optimizing algorithm further comprises: genetic algorithm, particle swarm algorithm, ant colony algorithm, and whale algorithm.
The beneficial effects of the invention are as follows:
(1) According to the invention, a digital twin model of the cooling tower, the cooling water pump and the water chilling unit in the central air conditioning system is established by adopting a mechanism modeling and data identification method, virtual simulation mapping is carried out on the cooling tower, the cooling water pump and the water chilling unit of the actual central air conditioning system, actually measured data are input for identification and correction, the precision of the model is improved, a foundation is provided for the subsequent establishment of a cooling tower water outlet temperature prediction model, the prediction of the cooling tower water outlet temperature model based on the digital twin model is realized, and the variable frequency operation decision of the cooling tower fan and the cooling water pump is made based on the model prediction;
(2) According to the invention, through preprocessing and principal component analysis and correlation analysis of the original sample data, important characteristic parameters are screened out, and influence of irrelevant factors is reduced;
(3) According to the method, an input data set is input into each intelligent prediction algorithm for training, so that a cooling tower water outlet temperature prediction model corresponding to a plurality of intelligent prediction algorithms is obtained; the D-S evidence theory is adopted to conduct weight extraction and fusion on the prediction results of the plurality of cooling tower water outlet temperature prediction models, a final cooling tower water outlet temperature prediction value is obtained, the weight fusion model is established through weight extraction and credibility function synthesis, and compared with the prediction of a single model, the model prediction accuracy can be effectively improved;
(4) According to the invention, the energy consumption of the cooling water system is taken as an objective function, corresponding constraint conditions are set, an intelligent optimizing algorithm is adopted to solve and obtain the operation frequency combination of the cooling water pump and the cooling tower fan with optimal energy consumption, and the cooling water pump and the cooling tower fan are regulated to perform variable frequency operation, so that the water outlet temperature of the cooling tower reaches a set value, the control of the water outlet temperature of the cooling tower is realized, the water outlet temperature of the cooling tower is ensured to reach the standard, the energy consumption of the cooling water system is optimal, and the energy saving effect is improved.
Additional features and advantages will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for controlling the outlet water temperature of a central air conditioner cooling tower based on a D-S evidence theory;
FIG. 2 is a schematic diagram of a central air conditioning system according to the present invention;
FIG. 3 is a schematic diagram of the process of weight extraction and fusion of the result of the predictive model based on the D-S evidence theory;
FIG. 4 is a flow chart of temperature control performed by optimizing a cooling water pump and a cooling tower fan according to the present invention;
FIG. 5 is a flowchart of the firefly optimizing algorithm of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Fig. 1 is a flow chart of a method for controlling the outlet water temperature of a central air conditioner cooling tower based on a D-S evidence theory.
As shown in fig. 1, embodiment 1 provides a method for controlling the outlet water temperature of a central air conditioner cooling tower based on D-S evidence theory, which includes:
s1, establishing a digital twin model of a cooling tower, a cooling water pump and a water chiller in a central air conditioning system by adopting a mechanism modeling and data identification method;
s2, collecting different types of sensor parameters in the running process of the central air conditioning system, and taking the sensor parameters as original sample data reflecting the water outlet temperature of the cooling tower; the raw sample data includes at least: the water inlet temperature of the cooling tower, the water inlet flow of the cooling tower, the air inlet quantity of the cooling tower, the air wet bulb temperature, the water-air mass ratio and the water outlet temperature of the cooling tower;
S3, preprocessing the original sample data, analyzing principal components and performing correlation analysis to obtain an input data set, and inputting the input data set into each intelligent prediction algorithm for training to obtain cooling tower water outlet temperature prediction models corresponding to the intelligent prediction algorithms;
s4, carrying out weight extraction and fusion on prediction results of the plurality of cooling tower water outlet temperature prediction models by adopting a D-S evidence theory to obtain a final cooling tower water outlet temperature prediction value;
and S5, comparing the predicted value of the water outlet temperature of the cooling tower with a set water outlet temperature value of the cooling tower, if the predicted value of the water outlet temperature of the cooling tower is inconsistent with the set water outlet temperature value of the cooling tower, setting corresponding constraint conditions by taking the energy consumption of a cooling water system as an objective function, solving and obtaining the operation frequency combination of the cooling water pump and the cooling tower fan with optimal energy consumption by adopting an intelligent optimizing algorithm, and then adjusting the variable frequency operation of the cooling water pump and the cooling tower fan to enable the water outlet temperature of the cooling tower to reach a set value so as to realize the control of the water outlet temperature of the cooling tower.
Fig. 2 is a schematic structural diagram of a central air conditioning system according to the present invention.
In the embodiment, as shown in fig. 2, in step S1, a digital twin model of a cooling tower, a cooling water pump and a chiller in a central air conditioning system is established by adopting a mechanism modeling and data identification method, which specifically includes:
The water chiller is used for providing chilled water with a certain temperature for the tail end of a physical model of the water chiller, and comprises a compressor, an evaporator, a condenser and a throttle valve;
constructing a physical model, a logical model and a simulation model of the cooling tower;
constructing a physical model, a logical model and a simulation model of the cooling water pump; wherein, the liquid crystal display device comprises a liquid crystal display device,
the construction of the logic model comprises the following steps: establishing a controllable closed-loop logic model according to the logic mechanism relation among all physical entities of the central air conditioning system, and mapping the physical model to the logic model;
the construction of the simulation model comprises the following steps: constructing a central air conditioning system simulation model based on the collected operation data, state data and physical attribute data of the central air conditioning system;
carrying out virtual-real fusion on the physical model, the logic model and the simulation model, and constructing a system-level digital twin model of the physical entities of the cooling tower, the cooling water pump and the water chiller in the virtual space;
and accessing the multi-working-condition real-time operation data of the cooling tower, the cooling water pump and the water chilling unit into a system digital twin model, and carrying out self-adaptive identification correction on the simulation result of the system digital twin model by adopting a reverse identification method to obtain the digital twin model of the cooling tower, the cooling water pump and the water chilling unit in the central air conditioning system after identification correction.
In this embodiment, the building of the simulation model of the water chiller includes:
neglecting the suction and exhaust pressure loss of the compressor and neglecting the heat exchange between the compressor and the environment, and establishing a compressor model to be expressed as:
wherein m is r Is the refrigerant mass flow; v (V) th Gas delivery capacity is a mechanism of compression; v 1 The specific volume of suction gas for the compressor; ζ is the gas transmission coefficient; p (P) ths Theoretical power consumption of the isentropic compression process of the compressor; p (P) i The power consumption of the actual compression process of the compressor is the indicated power; p (P) el The electric power input for the actual compression process of the compressor, namely the power measured by a power meter; k is an isentropic compression index; p (P) e Is the evaporating pressure, i.e. the compressor suction pressure; p (P) k Is the condensing pressure, i.e., compressor discharge pressure; η (eta) i An indicated efficiency for the compressor; η (eta) el Is the electrical efficiency of the compressor; h is a 2 Enthalpy for the compressor outlet refrigerant; h is a 1 Enthalpy for the compressor inlet refrigerant;
the simulation model establishment of the condenser comprises the following steps:
neglecting heat exchange between the condenser and the outside, regarding the flow of the refrigerant and the cooling water as one-dimensional uniform flow, and obtaining the heat exchange process in the condenser is expressed as:
Q c =m w,c c p,w (t wo,c -t wi,c )=m r (h ri,c -h ro,c );
Q 1,c =K 1,c F 1,c Δt 1,c ;
Q 2,c =K 2,c F 2,c Δt 2,c ;
Q 3,c =K 3,c F 3,c Δt 3,c ;
wherein Q is c The total heat exchange amount of the condenser; m is m w,c Is the flow of cooling water; c p,w The constant pressure specific heat of water; t is t wi,c The inlet temperature of cooling water; t is t wo,c Is the cooling water outlet temperature; t is t ri,c Is the refrigerant inlet temperature; t is t ro,c Is the refrigerant outlet temperature; t is t r,c Is the condensation temperature; m is m r Is the refrigerant flow; h is a ri,c Is the enthalpy of the condenser inlet refrigerant; h is a ro,c Is the outlet enthalpy value of the condenser; q (Q) 1,c 、Q 2,c 、Q 3,c The heat exchange amount of the condenser superheat zone, the two-phase zone and the supercooling zone is respectively; f (F) 1,c 、F 2,c 、F 3,c The heat exchange areas of the condenser superheat zone, the two-phase zone and the supercooling zone are respectively; Δt (delta t) 1,c 、Δt 2,c 、Δt 3,c The heat exchange temperature difference is respectively the heat exchange temperature difference of the condenser superheat zone, the two-phase zone and the supercooling zone; k (K) 1,c 、K 2,c 、K 3,c The heat transfer coefficients of the condenser superheat zone, the two-phase zone and the supercooling zone are respectively;
the evaporator modeling includes:
neglecting heat exchange between the evaporator and the outside, regarding the flow of the refrigerant and the chilled water as one-dimensional uniform flow, and obtaining the heat exchange process in the evaporator is expressed as:
Q e =m w,e c p,w (t wi,e -t wo,e )=m r (1-x)(h ro,e -h ri,e );
Q 1,e =K 1,e F 1,e Δt 1,e ;
Q 2,e =K 2,e F 2,e Δt 2,e ;
wherein Q is e Heat exchange capacity for the evaporator; m is m w,e Is the flow of the chilled water; t is t wi,e Chilled water temperature for evaporator inlet; t is t wo,e Chilled water temperature for evaporator outlet; t is t w1,e Chilled water temperature for the inlet of the two-phase zone; h is a ri,e Is the evaporator inlet enthalpy; h is a ro,e Is the evaporator outlet enthalpy; x is the dryness of the refrigerant at the inlet of the evaporator; q (Q) 1,e Heat exchange amount for the overheat area of the evaporator; q (Q) 2,e Heat exchange capacity is carried out for the two-phase region of the evaporator; Δt (delta t) 1,e The heat exchange temperature difference is the superheat region of the evaporator; Δt (delta t) 2,e The heat exchange temperature difference is the two-phase area of the evaporator; t is t ro,e The suction temperature of the compressor, namely the outlet refrigerant temperature of the evaporator; t is t r,e Is the evaporation temperature;
the simulation model establishment of the throttle valve comprises the following steps:
the thermal expansion valve is formed by the pressure P of a temperature sensing medium in a temperature sensing bulb b Providing a valve opening force from the steam pressure P c And a spring force providing a valve closing force, the spring force being minimal when the valve is in a closed state, ΔP min The method comprises the steps of carrying out a first treatment on the surface of the Valve displacement y and P b 、P c 、ΔP min The relationship between them is expressed as: y=k (P b -P c -ΔP min ) The method comprises the steps of carrying out a first treatment on the surface of the k is the reciprocal of the spring rate;
the simulation model establishment of the cooling water pump comprises the following steps:
the rotation speed ratio f of the water pump is defined as the rotation speed n of the water pump motor and the rated motor rotation speed n 0 The ratio is expressed as:
the relationship between the pump lift, pump efficiency and pump flow and speed ratio is expressed as:
wherein H is pu Is the lift of the water pump; m is m w Is the mass flow of the water pump; η (eta) pu The efficiency of the water pump is achieved; h is a 01 、h 02 、h 03 、h 11 、h 12 、h 13 Fitting coefficients;
the simulation model establishment of the cooling tower comprises the following steps:
the total heat transfer rate of the cooling tower is expressed as: q=ε a m a (h a,w,i -h a,i );ε a Heat transfer rate for the air side; m is m a Is the mass flow of air; h is a a,w,i The enthalpy value of the humid air at the cooling water inlet; h is a a,i An enthalpy value for the humid air at the cooling tower air inlet;
the mass flow of water at the water outlet of the cooling tower is expressed as: m is m w,o =m w,i -m a (w a,o -w a,i )+m m ;m m The mass flow rate of the make-up water; w (w) a,o The air moisture content at the air outlet of the cooling tower; w (w) a,i The air humidity content at the air inlet of the cooling tower; m is m w,i Is the mass flow of the water inlet and the water outlet of the cooling tower.
In this embodiment, in step S3, the preprocessing, principal component analysis, and correlation analysis are performed on the original sample data to obtain an input data set, which specifically includes:
preprocessing the original sample data, including: the method comprises the steps of missing value filling, repeated value deleting, normalization and wavelet noise filtering;
the method for performing data dimension reduction on the preprocessed data by adopting a principal component analysis method comprises the following steps: the preprocessed data are formed into an n-row m-column matrix X according to columns, each row of the matrix X is subjected to zero-mean, namely the mean value of the row is subtracted, and a covariance matrix is obtained; then, the eigenvalues and the corresponding eigenvectors of the covariance matrix are obtained, the eigenvectors are arranged into a matrix according to the corresponding eigenvalues from top to bottom, the first k rows are taken to form a matrix P, and Y=PX is the data after dimension reduction to k dimensions;
calculating the correlation coefficient of the cooling tower water outlet temperature and other data by using the Pearson correlation coefficient R, wherein the calculation comprises the following steps: and calculating the correlation coefficient between two groups of different data, if the Pelson correlation coefficient value is larger than the coefficient threshold value, judging the data as data with high correlation with the control of the cooling tower water outlet temperature, and taking the data as an input data set of a cooling tower water outlet temperature prediction model.
Fig. 3 is a schematic diagram of a process for extracting and fusing weights of the results of a prediction model based on D-S evidence theory according to the present invention.
In the embodiment, as shown in fig. 3, in step S3, an input data set is input into each intelligent prediction algorithm to perform training, so as to obtain a cooling tower water outlet temperature prediction model corresponding to a plurality of intelligent prediction algorithms, which specifically includes:
inputting the input data set into each intelligent prediction algorithm for training to obtain a cooling tower water outlet temperature prediction model corresponding to each intelligent prediction algorithm; each intelligent prediction algorithm comprises at least: support vector machine algorithm, convolutional neural network algorithm, XGBoost algorithm, BP neural network algorithm and Bayesian network algorithm;
and predicting the water outlet temperature of the cooling tower through a plurality of cooling tower water outlet temperature prediction models respectively to obtain a prediction result P 1 、P 2 、P 3 ……P i And calculates the prediction result P i Error e from true value R i Expressed as:
in this embodiment, in step S4, the weight extraction and fusion are performed on the prediction results of the plurality of cooling tower water outlet temperature prediction models by using the D-S evidence theory to obtain a final cooling tower water outlet temperature prediction value, which specifically includes:
according to error e i Calculating the weight w of the fused sample i Expressed as:epsilon is the introduced coefficient;
let the predicted value of the cooling tower water outlet temperature predicted model be P i The corresponding weight is w i In the recognition frame Θ= { P 1 ,P 2 ,P 3 …P i Establishing a basic credibility allocation m, wherein the corresponding basic credibility value is expressed as: m is m j (P i )=w i The method comprises the steps of carrying out a first treatment on the surface of the j is the corresponding predicted date;
set Bel j For the confidence function corresponding to the confidence value, firstly 2 times of fusion are carried out on the confidence function, then 3 times of fusion are carried out on the 2 times of fusion result and the confidence function corresponding to the predicted value of the next day, and the like until the fusion is finished, and the result is expressed as:and simultaneously, the corresponding basic credibility value is expressed as: m is m c (P 1 )、m c (P 2 )、m c (P 3 )、……、m c (P i ) The basic credibility value is the weight fused with the water outlet temperature prediction model of the cooling tower on day c;
assume that the prediction results of the water outlet temperature prediction models of the cooling towers on the c days are respectively P 1 c 、……、P i c The final result of the fusion of the predicted data of the water outlet temperature of the cooling tower on day c is expressed as:
in practical application, taking three cooling tower outlet water temperature prediction models as examples, a process for predicting the cooling tower outlet water temperature based on a D-S evidence theory is described, and the concrete steps are as follows:
Respectively inputting the input data set into a support vector machine algorithm, a convolutional neural network algorithm and an XGBoost algorithm for training to obtain cooling tower water outlet temperature prediction models corresponding to the three intelligent prediction algorithms;
the water outlet temperature of the cooling tower is respectively predicted by the three cooling tower water outlet temperature prediction models to obtain a prediction result P 1 、P 2 、P 3 And calculate the prediction result P 1 、P 2 、P 3 Error e from true value R 1 、e 2 、e 3 ;
According to error e 1 、e 2 、e 3 Calculate the corresponding weight w 1 、w 2 、w 3 ;
In the recognition framework Θ= { P 1 ,P 2 ,P 3 Establishing a basic credibility allocation m, wherein the corresponding basic credibility value is expressed as: m is m j (P i )=w i ,i=1,2,3;
Assuming that the basic confidence values corresponding to the predicted values of the water outlet temperature of the cooling tower for 15 to 20 days are m respectively j (P i ) (i=1, 2,3; j= 15,16,17,18,19,20) whose corresponding belief function is Bel j The method comprises the steps of carrying out a first treatment on the surface of the Fusing the confidence functions corresponding to 15 days and 16 days, marking the basic confidence corresponding to the fused result as m, and marking the corresponding synthesized confidence function as
2-time fusion is carried out on the synthesized credibility function Bel and the credibility function corresponding to the 17-day cooling tower water outlet temperature predicted value; 3-time fusion is carried out on the 2-time fusion result and the credibility function corresponding to the 18-day predicted value, and the same is carried out until 5-time fusion is finished, and the result is recorded as At the same time, the basic confidence value corresponding to the result is recorded as m c (P 1 )、m c (P 2 )、m c (P 3 );
Assume that the prediction results of the three models on the water supply temperature of the 23-day cooling tower are respectively P 1 23 、The final result of the 23-day load prediction data fusion can be expressed as:
since 24 times of the daily cooling tower water supply temperature prediction are performed, that is, each 1 hour interval, the final result is a vector containing 24 elements.
Fig. 4 is a flow chart of temperature control performed by optimizing the cooling water pump and the cooling tower fan according to the present invention.
In the embodiment, as shown in fig. 4, in step S5, the energy consumption of the cooling water system is taken as an objective function, and the setting of the corresponding constraint conditions specifically includes:
establishing an energy consumption objective function of a cooling water system:
minP total =min(P pump +P tower +P chiller );P pump 、P tower 、P chiller the energy consumption of the cooling water pump, the cooling tower and the water chilling unit are respectively;
ρ w is the density of water; g is the local gravitational acceleration; h is the lift; g w Is the volume flow of the water flow; η (eta) p The efficiency of the water pump is achieved; η (eta) m The motor efficiency is; n is n f The frequency converter efficiency;
k is the number of variable frequency fans in one cooling tower; n is n i Is the actual rotation speed of the variable frequency fan;n o The rated rotation speed of the variable frequency fan is set; p (P) max The rated power of a variable-frequency fan is set;
r is the real-time load rate of the water chilling unit, +. >Q e For the real-time cold load of the water chilling unit, Q 0 Rated cold load for the water chilling unit; t (T) e 、T c The evaporation temperature and the condensation temperature of the water chilling unit are respectively;
setting constraint conditions:
cooling water pump frequency constraint:wherein (1)>Is the upper limit of the power consumption of the cooling water pump>Lower limit of power consumption of cooling water pump, F pump Is the actual value of the power consumption of the cooling water pump;
cooling tower fan frequency constraint:wherein (1)>Is the lower limit of the fan frequency of the cooling tower,Is the upper limit of the fan frequency of the cooling tower, F tower Is the actual value of the cooling tower fan frequency;
cooling water inlet temperature constraint:wherein (1)>Is the water inlet temperature of cooling water, < >>Is the lower limit of the water inlet temperature of cooling water, < >>Is the upper limit of the water inlet temperature of the cooling water;
the number of cooling towers is restricted:wherein N is tower For the number of cooling towers, < > or >>Is the lower limit of the number of cooling towers to be operated, < >>Is the upper limit of the number of cooling towers;
and (3) constraining the number of cooling water pumps:wherein N is pump The number of the cooling water pumps is the number,The lower limit of the number of the cooling water pumps is->Is the upper limit of the number of the cooling water pumps.
Fig. 5 is a flowchart of the firefly optimizing algorithm according to the present invention.
In the embodiment, as shown in fig. 5, in step S5, an intelligent optimizing algorithm is adopted to solve and obtain an operation frequency combination of a cooling water pump and a cooling tower fan with optimal energy consumption, which specifically includes:
Initializing a firefly optimizing algorithm population: setting the population quantity of fireflies as M, the absorption coefficient of the medium to light as gamma and the initial attraction degree beta 0 ;
Calculating the fitness value of each firefly according to the position of the firefly, wherein the higher the fitness value is, the higher the firefly brightness is;
each firefly moves to all fireflies with higher brightness than the fireflies, and a moving distance calculation formula is expressed as follows:
s i ' is a position of firefly that is brighter than the ith individual; s is(s) i ,s j Is the solution space position of firefly i, j; r is the distance between the ith firefly and the jth firefly; zeta type toy i Is a random disturbance of firefly i; alpha is the step factor of the disturbance;
the individuals with the biggest brightness in the firefly population update the positions of the individuals;
calculating the adaptability value of a new position where the firefly flies to all other individuals with higher brightness than the firefly, if the position is better than the position before flying, the firefly flies to the new position, otherwise, the firefly stays in place;
if the algorithm reaches the maximum iteration times, outputting the searched optimal position of the firefly as a solution, otherwise, recalculating the fitness value of each firefly;
and obtaining the operation frequency combination of the cooling water pump and the cooling tower fan with optimal energy consumption based on the optimal firefly position.
In this embodiment, the intelligent optimization algorithm further includes: genetic algorithm, particle swarm algorithm, ant colony algorithm, and whale algorithm.
According to the invention, a digital twin model of the cooling tower, the cooling water pump and the water chilling unit in the central air conditioning system is established by adopting a mechanism modeling and data identification method, virtual simulation mapping is carried out on the cooling tower, the cooling water pump and the water chilling unit of the actual central air conditioning system, actually measured data are input for identification and correction, the accuracy of the model is improved, a foundation is provided for the subsequent establishment of a cooling tower water outlet temperature prediction model, the prediction of the cooling tower water outlet temperature model based on the digital twin model is realized, and the variable frequency operation decision of the cooling tower fan and the cooling water pump is made based on the model prediction.
According to the invention, the important characteristic parameters are screened out by preprocessing, principal component analysis and correlation analysis on the original sample data, so that the influence of irrelevant factors is reduced.
According to the method, an input data set is input into each intelligent prediction algorithm for training, so that a cooling tower water outlet temperature prediction model corresponding to a plurality of intelligent prediction algorithms is obtained; and the D-S evidence theory is adopted to conduct weight extraction and fusion on the prediction results of the plurality of cooling tower water outlet temperature prediction models, a final cooling tower water outlet temperature prediction value is obtained, and a weight fusion model is established through weight extraction and credibility function synthesis, so that compared with the prediction of a single model, the model prediction precision can be effectively improved.
According to the invention, the energy consumption of the cooling water system is taken as an objective function, corresponding constraint conditions are set, an intelligent optimizing algorithm is adopted to solve and obtain the operation frequency combination of the cooling water pump and the cooling tower fan with optimal energy consumption, and the cooling water pump and the cooling tower fan are regulated to perform variable frequency operation, so that the water outlet temperature of the cooling tower reaches a set value, the control of the water outlet temperature of the cooling tower is realized, the water outlet temperature of the cooling tower is ensured to reach the standard, the energy consumption of the cooling water system is optimal, and the energy saving effect is improved.
In the several embodiments provided in this application, it should be understood that the disclosed systems and methods may be implemented in other ways as well. The system embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present invention may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored on a computer readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
With the above-described preferred embodiments according to the present invention as an illustration, the above-described descriptions can be used by persons skilled in the relevant art to make various changes and modifications without departing from the scope of the technical idea of the present invention. The technical scope of the present invention is not limited to the description, but must be determined according to the scope of claims.
Claims (7)
1. The method for controlling the outlet water temperature of the cooling tower of the central air conditioner based on the D-S evidence theory is characterized by comprising the following steps:
s1, establishing a digital twin model of a cooling tower, a cooling water pump and a water chiller in a central air conditioning system by adopting a mechanism modeling and data identification method; the method specifically comprises the following steps:
constructing a physical model, a logical model and a simulation model of a water chilling unit, wherein the water chilling unit is used for providing chilled water with a certain temperature for the tail end of the physical model of the water chilling unit, and comprises a compressor, an evaporator, a condenser and a throttle valve;
constructing a physical model, a logical model and a simulation model of the cooling tower;
constructing a physical model, a logical model and a simulation model of the cooling water pump; wherein, the liquid crystal display device comprises a liquid crystal display device,
the construction of the logic model comprises the following steps: establishing a controllable closed-loop logic model according to the logic mechanism relation among all physical entities of the central air conditioning system, and mapping the physical model to the logic model;
the construction of the simulation model comprises the following steps: constructing a central air conditioning system simulation model based on the collected operation data, state data and physical attribute data of the central air conditioning system;
carrying out virtual-real fusion on the physical model, the logic model and the simulation model, and constructing a system-level digital twin model of physical entities of the cooling tower, the cooling water pump and the water chiller in a virtual space;
The multi-working-condition real-time operation data of the cooling tower, the cooling water pump and the water chilling unit are accessed into the system-level digital twin model, and a reverse identification method is adopted to carry out self-adaptive identification correction on the simulation result of the system-level digital twin model, so that the digital twin model of the cooling tower, the cooling water pump and the water chilling unit in the central air conditioning system after identification correction is obtained;
s2, collecting different types of sensor parameters in the running process of the central air conditioning system, and taking the sensor parameters as original sample data reflecting the water outlet temperature of the cooling tower; the original sample data at least comprises cooling tower water inlet temperature, cooling tower water inlet flow, cooling tower air inlet quantity, air wet bulb temperature, water-air mass ratio and cooling tower water outlet temperature;
s3, preprocessing the original sample data, analyzing principal components and performing correlation analysis to obtain an input data set, and inputting the input data set into each intelligent prediction algorithm for training to obtain a plurality of cooling tower water outlet temperature prediction models corresponding to the intelligent prediction algorithms;
s4, carrying out weight extraction and fusion on prediction results of the cooling tower water outlet temperature prediction models by adopting a D-S evidence theory to obtain a final cooling tower water outlet temperature prediction value;
S5, comparing the predicted value of the water outlet temperature of the cooling tower with a set water outlet temperature value of the cooling tower, if the predicted value of the water outlet temperature of the cooling tower is inconsistent, setting corresponding constraint conditions by taking the energy consumption of a cooling water system as an objective function, solving and obtaining the operation frequency combination of a cooling water pump and a cooling tower fan with optimal energy consumption by adopting an intelligent optimizing algorithm, and then controlling the water outlet temperature of the cooling tower to reach a set value by adjusting the variable frequency operation of the cooling water pump and the cooling tower fan;
the simulation model establishment of the water chilling unit comprises the following steps:
neglecting the suction and exhaust pressure loss of the compressor and neglecting the heat exchange between the compressor and the environment, and establishing a compressor model to be expressed as:
wherein m is r Is the refrigerant mass flow; v (V) th Gas delivery capacity is a mechanism of compression; v 1 The specific volume of suction gas for the compressor; ζ is the gas transmission coefficient; p (P) ths Theoretical power consumption of the isentropic compression process of the compressor; p (P) i The power consumption of the actual compression process of the compressor is the indicated power; p (P) el The electric power input for the actual compression process of the compressor, namely the power measured by a power meter; k is an isentropic compression index; p (P) e Is the evaporating pressure, i.e. the compressor suction pressure; p (P) k Is the condensing pressure, i.e., compressor discharge pressure; η (eta) i An indicated efficiency for the compressor; η (eta) el Is the electrical efficiency of the compressor; h is a 2 Enthalpy for the compressor outlet refrigerant; h is a 1 Enthalpy for the compressor inlet refrigerant;
the simulation model establishment of the condenser comprises the following steps:
neglecting heat exchange between the condenser and the outside, regarding the flow of the refrigerant and the cooling water as one-dimensional uniform flow, and obtaining the heat exchange process in the condenser is expressed as:
Q c =m w,c c p,w (t wo,c -t wi,c )=m r (h ri,c -h ro,c );
Q 1,c =K 1,c F 1,c Δt 1,c ;
Q 2,c =K 2,c F 2,c Δt 2,c ;
Q 3,c =K 3,c F 3,c Δt 3,c ;
wherein Q is c The total heat exchange amount of the condenser; m is m w,c Is the flow of cooling water; c p,w The constant pressure specific heat of water; t is t wi,c The inlet temperature of cooling water; t is t wo,c Is the cooling water outlet temperature; t is t ri,c Is the refrigerant inlet temperature; t is t ro,c Is the refrigerant outlet temperature; t is t r,c Is the condensation temperature; m is m r Is the refrigerant flow; h is a ri,c Is the enthalpy of the condenser inlet refrigerant; h is a ro,c Is the outlet enthalpy value of the condenser; q (Q) 1,c 、Q 2,c 、Q 3,c The heat exchange amount of the condenser superheat zone, the two-phase zone and the supercooling zone is respectively; f (F) 1,c 、F 2,c 、F 3,c The heat exchange areas of the condenser superheat zone, the two-phase zone and the supercooling zone are respectively; Δt (delta t) 1,c 、Δt 2,c 、Δt 3,c The heat exchange temperature difference is respectively the heat exchange temperature difference of the condenser superheat zone, the two-phase zone and the supercooling zone; k (K) 1,c 、K 2,c 、K 3,c The heat transfer coefficients of the condenser superheat zone, the two-phase zone and the supercooling zone are respectively;
the simulation model establishment of the evaporator comprises the following steps:
neglecting heat exchange between the evaporator and the outside, regarding the flow of the refrigerant and the chilled water as one-dimensional uniform flow, and obtaining the heat exchange process in the evaporator is expressed as:
Q e =m w,e c p,w (t wi,e -t wo,e )=m r (1-x)(h ro,e -h ri,e );
Q 1,e =K 1,e F 1,e Δt 1,e ;
Q 2,e =K 2,e F 2,e Δt 2,e ;
Wherein Q is e Heat exchange capacity for the evaporator; m is m w,e Is the flow of the chilled water; t is t wi,e Chilled water temperature for evaporator inlet; t is t wo,e Chilled water temperature for evaporator outlet; t is t w1,e Chilled water temperature for the inlet of the two-phase zone; h is a ri,e Is the evaporator inlet enthalpy; h is a ro,e Is the evaporator outlet enthalpy; x is the dryness of the refrigerant at the inlet of the evaporator; q (Q) 1,e Heat exchange amount for the overheat area of the evaporator; q (Q) 2,e Heat exchange capacity is carried out for the two-phase region of the evaporator; Δt (delta t) 1,e The heat exchange temperature difference is the superheat region of the evaporator; Δt (delta t) 2,e The heat exchange temperature difference is the two-phase area of the evaporator; t is t ro,e The suction temperature of the compressor, namely the outlet refrigerant temperature of the evaporator; t is t r,e Is the evaporation temperature;
the simulation model establishment of the throttle valve comprises the following steps:
the thermal expansion valve is formed by the pressure P of a temperature sensing medium in a temperature sensing bulb b Providing a valve opening force from the steam pressure P c And a spring force providing a valve closing force, the spring force being minimal when the valve is in a closed state, ΔP min The method comprises the steps of carrying out a first treatment on the surface of the Valve displacement y and P b 、P c 、ΔP min The relationship between them is expressed as: y=k (P b -P c -ΔP min ) The method comprises the steps of carrying out a first treatment on the surface of the k is the reciprocal of the spring rate;
the simulation model establishment of the cooling water pump comprises the following steps:
the rotation speed ratio f of the water pump is defined as the rotation speed n of the water pump motor and the rated motor rotation speed n 0 The ratio is expressed as:
the relationship between the pump lift, pump efficiency and pump flow and speed ratio is expressed as:
Wherein H is pu Is the lift of the water pump; m is m w Is the mass flow of the water pump; η (eta) pu The efficiency of the water pump is achieved; h is a 01 、h 02 、h 03 、h 11 、h 12 、h 13 Fitting coefficients;
the simulation model establishment of the cooling tower comprises the following steps:
the total heat transfer rate of the cooling tower is expressed as: q=ε a m a (h a,w,i -h a,i );ε a Heat transfer rate for the air side; m is m a Is the mass flow of air; h is a a,w,i The enthalpy value of the humid air at the cooling water inlet; h is a a,i An enthalpy value for the humid air at the cooling tower air inlet;
the mass flow of water at the water outlet of the cooling tower is expressed as: m is m w,o =m w,i -m a (w a,o -w a,i )+m m ;m m The mass flow rate of the make-up water; w (w) a,o The air moisture content at the air outlet of the cooling tower; w (w) a,i The air humidity content at the air inlet of the cooling tower; m is m w,i Is the mass flow of the water inlet and the water outlet of the cooling tower.
2. The method for controlling the outlet water temperature of the central air conditioning cooling tower based on the D-S evidence theory according to claim 1, wherein in the step S3, the raw sample data is preprocessed, analyzed for principal components, and analyzed for correlation to obtain an input data set, and the method specifically comprises the following steps:
preprocessing the original sample data, including: filling missing values, deleting repeated values, normalizing and wavelet noise filtering;
the method for performing data dimension reduction on the preprocessed data by adopting a principal component analysis method comprises the following steps: the preprocessed data are formed into an n-row m-column matrix X according to columns, each row of the matrix X is subjected to zero-mean, namely the mean value of the row is subtracted, and a covariance matrix is obtained; then, the eigenvalues and the corresponding eigenvectors of the covariance matrix are obtained, the eigenvectors are arranged into a matrix according to the corresponding eigenvalues from top to bottom, the first k rows are taken to form a matrix P, and Y=PX is the data after dimension reduction to k dimensions;
Calculating the correlation coefficient of the cooling tower water outlet temperature and other data by using the Pearson correlation coefficient R, wherein the calculation comprises the following steps: and calculating the correlation coefficient between two groups of different data, if the Pelson correlation coefficient value is larger than the coefficient threshold value, judging the data as data with high correlation with the control of the cooling tower water outlet temperature, and taking the data as an input data set of a cooling tower water outlet temperature prediction model.
3. The method for controlling the outlet water temperature of the central air conditioner cooling tower based on the D-S evidence theory according to claim 1, wherein in the step S3, an input data set is input into each intelligent prediction algorithm for training, so as to obtain a cooling tower outlet water temperature prediction model corresponding to a plurality of intelligent prediction algorithms, and the method specifically comprises the following steps:
inputting an input data set into each intelligent prediction algorithm for training to obtain a cooling tower water outlet temperature prediction model corresponding to each intelligent prediction algorithm; the intelligent prediction algorithm at least comprises: support vector machine algorithm, convolutional neural network algorithm, XGBoost algorithm, BP neural network algorithm and Bayesian network algorithm;
4. the method for controlling the outlet water temperature of the central air-conditioning cooling tower based on the D-S evidence theory according to claim 1, wherein in the step S4, the D-S evidence theory is adopted to extract and fuse the predicted results of the plurality of cooling tower outlet water temperature prediction models, so as to obtain the final cooling tower outlet water temperature predicted value, and the method specifically comprises the following steps:
according to error e i Calculating the weight w of the fused sample i Expressed as:epsilon is the introduced coefficient;
setting the predicted value of the cooling tower water outlet temperature prediction model as P i The corresponding weight is w i In the recognition frame Θ= { P 1 ,P 2 ,P 3 …P i Establishing a basic credibility allocation m, wherein the corresponding basic credibility value is expressed as: m is m j (P i )=w i The method comprises the steps of carrying out a first treatment on the surface of the j is the corresponding predicted date;
set Bel j For the confidence function corresponding to the confidence value, firstly 2 times of fusion are carried out on the confidence function, then 3 times of fusion are carried out on the 2 times of fusion result and the confidence function corresponding to the predicted value of the next day, and the like until the fusion is finished, and the result is expressed as:and simultaneously, the corresponding basic credibility value is expressed as: m is m c (P 1 )、m c (P 2 )、m c (P 3 )、……、m c (P i ) The basic credibility value is the weight fused with the water outlet temperature prediction model of the cooling tower on day c;
Assume that the prediction results of the plurality of cooling tower water outlet temperature prediction models on the water outlet temperature of the cooling tower on day c are respectively as followsThe final result of the c-day cooling tower water outlet temperature prediction data fusion is expressed as:
5. the method for controlling the outlet water temperature of the central air conditioning cooling tower based on the D-S evidence theory according to claim 1, wherein in the step S5, the energy consumption of the cooling water system is taken as an objective function, and the corresponding constraint conditions are set, which specifically include:
establishing an energy consumption objective function of a cooling water system:
minP total =min(P pump +P tower +P chiller ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein P is pump 、P tower 、P chiller The energy consumption of the cooling water pump, the cooling tower and the water chilling unit are respectively;
wherein ρ is w Is the density of water; g is the local gravitational acceleration; h is the lift; g w Is the volume flow of the water flow; η (eta) p The efficiency of the water pump is achieved; η (eta) m The motor efficiency is; n is n f The frequency converter efficiency; />
Wherein k is the number of variable frequency fans in one cooling tower; n is n i The actual rotating speed of the variable frequency fan; n is n o The rated rotation speed of the variable frequency fan is set; p (P) max The rated power of a variable-frequency fan is set;
wherein r is the real-time load rate of the water chilling unit, < ->Q e For the real-time cold load of the water chilling unit, Q 0 Rated cold load for the water chilling unit; t (T) e 、T c Respectively water coolersGroup evaporation temperature and condensation temperature;
Setting constraint conditions:
cooling water pump frequency constraint:wherein (1)>Is the upper limit of the power consumption of the cooling water pump>Lower limit of power consumption of cooling water pump, F pump Is the actual value of the power consumption of the cooling water pump;
cooling tower fan frequency constraint:wherein (1)>Is the lower limit of the fan frequency of the cooling tower, +.>Is the upper limit of the fan frequency of the cooling tower, F tower Is the actual value of the cooling tower fan frequency;
cooling water inlet temperature constraint:wherein (1)>Is the water inlet temperature of cooling water, < >>Is the lower limit of the water inlet temperature of cooling water, < >>Is the upper limit of the water inlet temperature of the cooling water;
the number of cooling towers is restricted:wherein N is tower For the number of cooling towers, < > or >>Is the lower limit of the number of cooling towers to be operated, < >>Is the upper limit of the number of cooling towers;
6. The method for controlling the outlet water temperature of the cooling tower of the central air conditioner based on the D-S evidence theory according to claim 5, wherein in the step S5, an intelligent optimizing algorithm is adopted to solve and obtain the operation frequency combination of the cooling water pump and the cooling tower fan with optimal energy consumption, and the method specifically comprises the following steps:
Initializing a firefly optimizing algorithm population: setting the population quantity of fireflies as M, the absorption coefficient of the medium to light as gamma and the initial attraction degree beta 0 ;
Calculating the fitness value of each firefly according to the position of the firefly, wherein the higher the fitness value is, the higher the firefly brightness is;
each firefly moves to all fireflies with higher brightness than the fireflies, and a moving distance calculation formula is expressed as follows:
wherein s is i ' is a position of firefly that is brighter than the ith individual; s is(s) i ,s j Is the solution space position of firefly i, j; r is the distance between the ith firefly and the jth firefly; zeta type toy i Is a random disturbance of firefly i; alpha is the step factor of the disturbance;
the individuals with the biggest brightness in the firefly population update the positions of the individuals;
calculating the adaptability value of a new position where the firefly flies to all other individuals with higher brightness than the firefly, if the position is better than the position before flying, the firefly flies to the new position, otherwise, the firefly stays in place;
if the algorithm reaches the maximum iteration times, outputting the searched optimal position of the firefly as a solution, otherwise, recalculating the fitness value of each firefly;
and obtaining the operation frequency combination of the cooling water pump and the cooling tower fan with optimal energy consumption based on the optimal firefly position.
7. The method for controlling the outlet water temperature of the central air conditioner cooling tower based on the D-S evidence theory according to claim 1, wherein the intelligent optimizing algorithm further comprises a genetic algorithm, a particle swarm algorithm, an ant colony algorithm and a whale algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111614353.7A CN114370696B (en) | 2021-12-27 | 2021-12-27 | D-S evidence theory-based central air conditioner cooling tower water outlet temperature control method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111614353.7A CN114370696B (en) | 2021-12-27 | 2021-12-27 | D-S evidence theory-based central air conditioner cooling tower water outlet temperature control method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114370696A CN114370696A (en) | 2022-04-19 |
CN114370696B true CN114370696B (en) | 2023-04-21 |
Family
ID=81142475
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111614353.7A Active CN114370696B (en) | 2021-12-27 | 2021-12-27 | D-S evidence theory-based central air conditioner cooling tower water outlet temperature control method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114370696B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115115143B (en) * | 2022-08-25 | 2022-11-25 | 南京群顶科技有限公司 | Method for calculating optimal number of opened cooling tower and minimum operation energy consumption based on AI algorithm |
CN115860445B (en) * | 2022-11-15 | 2024-02-09 | 中核陕西铀浓缩有限公司 | Multi-level collaborative scheduling method for uranium enrichment refrigerating unit and closed cooling tower |
CN116187598B (en) * | 2023-04-28 | 2023-07-04 | 深圳市科中云技术有限公司 | Building-based virtual power plant load prediction method |
CN116592467A (en) * | 2023-06-12 | 2023-08-15 | 上海联元智能科技有限公司 | Central air conditioner energy saving method and system |
CN117232097B (en) * | 2023-11-09 | 2024-02-20 | 上海轻环能源科技有限公司 | Central air conditioner refrigerating station optimal control method and system based on self-learning fusion model |
CN117450630B (en) * | 2023-12-21 | 2024-02-27 | 上海安巢在线控制技术股份有限公司 | Air conditioner energy consumption control method and system based on cold water pump flow |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6816075B2 (en) * | 2001-02-21 | 2004-11-09 | 3M Innovative Properties Company | Evidence and property tracking for law enforcement |
CN104374053B (en) * | 2014-11-25 | 2017-02-22 | 珠海格力电器股份有限公司 | Intelligent control method, device and system |
MX2021008139A (en) * | 2019-01-03 | 2021-11-12 | Aspen Compressor Llc | High performance compressors and vapor compression systems. |
-
2021
- 2021-12-27 CN CN202111614353.7A patent/CN114370696B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN114370696A (en) | 2022-04-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114370696B (en) | D-S evidence theory-based central air conditioner cooling tower water outlet temperature control method | |
CN114484731B (en) | Central air conditioner fault diagnosis method and device based on stacking fusion algorithm | |
Dizaji et al. | A comprehensive review of the Maisotsenko-cycle based air conditioning systems | |
CN113326651B (en) | Refrigerating station load and energy efficiency ratio dynamic modeling method based on T-S fuzzy model | |
Mohanraj et al. | Applications of artificial neural networks for refrigeration, air-conditioning and heat pump systems—A review | |
CN101393570B (en) | Operation emulation system for central air-conditioning | |
CN111735178A (en) | Air conditioner energy-saving system based on elite meaning and SVR regression algorithm and optimization method | |
CN102283283B (en) | Intelligentized superficial geothermal energy low-temperature grain storage system | |
CN107704875A (en) | Based on the building load Forecasting Methodology and device for improving IHCMAC neutral nets | |
CN1811306A (en) | Automatic volume regulating and controlling method for gas-burning machine heat pump | |
CN115115143B (en) | Method for calculating optimal number of opened cooling tower and minimum operation energy consumption based on AI algorithm | |
CN114688688B (en) | Intelligent refrigerating comfortable air conditioner based on deep learning | |
Eom et al. | Deep learning-based prediction method on performance change of air source heat pump system under frosting conditions | |
Jiang et al. | Dynamic modeling and economic model predictive control of a liquid desiccant air conditioning | |
CN114198881A (en) | Air conditioner control method and device and air conditioner | |
Wang et al. | Optimization of a hybrid ejector air conditioning system with PSOGA | |
Park et al. | Stacking deep transfer learning for short-term cross building energy prediction with different seasonality and occupant schedule | |
CN111735177A (en) | Central air conditioning system cold load prediction method based on SVR algorithm | |
Chen et al. | An hour-ahead predictive control strategy for maximizing natural ventilation in passive buildings based on weather forecasting | |
CN113375283A (en) | Air conditioner control method and air conditioner | |
US11580281B2 (en) | System and method for designing heating, ventilating, and air-conditioning (HVAC) systems | |
TW202204832A (en) | Air conditioning system control method configured to control an air-conditioning setting temperature of an air-conditioning system and implemented by an air-conditioning control device | |
CN112329813A (en) | Energy consumption prediction feature extraction method and system | |
CN111473480A (en) | Central air conditioner energy-saving control method based on decision tree classification | |
CN110986492A (en) | Freezing type dryer and control method thereof |
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 | ||
CB02 | Change of applicant information |
Address after: 310000 rooms 208, 209-1, 209-2, building 2, 88 Longyuan Road, Cangqian street, Yuhang District, Hangzhou City, Zhejiang Province Applicant after: Zhejiang Yingji Power Technology Co.,Ltd. Address before: 310000 rooms 208, 209-1, 209-2, building 2, 88 Longyuan Road, Cangqian street, Yuhang District, Hangzhou City, Zhejiang Province Applicant before: Hangzhou Yingji Power Technology Co.,Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |