CN110220288A - Central air-conditioning system intelligent optimized control method and device based on big data cloud platform - Google Patents
Central air-conditioning system intelligent optimized control method and device based on big data cloud platform Download PDFInfo
- Publication number
- CN110220288A CN110220288A CN201910446104.8A CN201910446104A CN110220288A CN 110220288 A CN110220288 A CN 110220288A CN 201910446104 A CN201910446104 A CN 201910446104A CN 110220288 A CN110220288 A CN 110220288A
- Authority
- CN
- China
- Prior art keywords
- air
- water
- ahu
- conditioning box
- chilled
- 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
- 238000004378 air conditioning Methods 0.000 title claims abstract description 242
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000005457 optimization Methods 0.000 claims abstract description 57
- 238000004891 communication Methods 0.000 claims abstract description 55
- 238000005265 energy consumption Methods 0.000 claims abstract description 44
- 238000001914 filtration Methods 0.000 claims abstract description 20
- 230000005540 biological transmission Effects 0.000 claims abstract description 10
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 288
- 238000005057 refrigeration Methods 0.000 claims description 96
- 238000001816 cooling Methods 0.000 claims description 80
- 239000000498 cooling water Substances 0.000 claims description 50
- 238000012706 support-vector machine Methods 0.000 claims description 11
- 238000010845 search algorithm Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 239000008400 supply water Substances 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 239000002245 particle Substances 0.000 claims description 5
- 238000002922 simulated annealing Methods 0.000 claims description 5
- 230000002068 genetic effect Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000011426 transformation method Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 230000004044 response Effects 0.000 claims description 2
- 238000009833 condensation Methods 0.000 claims 1
- 230000005494 condensation Effects 0.000 claims 1
- 238000010025 steaming Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 17
- 238000005516 engineering process Methods 0.000 description 7
- 230000013016 learning Effects 0.000 description 5
- 238000004134 energy conservation Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000007710 freezing Methods 0.000 description 3
- 230000008014 freezing Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000001704 evaporation Methods 0.000 description 2
- 230000008020 evaporation Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- 241001515806 Stictis Species 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000001276 controlling effect Effects 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
- 238000013499 data model Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000013332 literature search Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000021715 photosynthesis, light harvesting Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
-
- 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
- F24F11/88—Electrical aspects, e.g. circuits
-
- 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
- F24F11/89—Arrangement or mounting of control or safety devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/10—Temperature
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/20—Humidity
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses a kind of central air-conditioning system intelligent optimized control methods and device based on big data cloud platform, it is related to air-conditioning technical field, including data transmission module, server data platform, various sensors, controller, the data transmission module includes data filtering module, data I/O interface input terminal, data I/O interface output end, RS485 communication interface, 4G/5G communication interface, WAN communication interface, power supply, data connection port.The present invention considers influence of the operating condition of each power-equipment of central air-conditioning system to whole system energy consumption comprehensively, further promotes central air-conditioning system Optimization of Energy Saving effect.Using big data platform and intelligent algorithm, substantially increase the energy consumption model of system dynamic equipment or the precision of performance model, higher-dimension Optimized model is solved using biological evolution algorithm, optimization computational efficiency is effectively increased, to realize that the on-line optimization of large-scale centralized air-conditioning system provides necessary condition.
Description
Technical field
The present invention relates to air-conditioning technical field more particularly to a kind of central air-conditioning system intelligence based on big data cloud platform
Optimal control method and device.
Background technique
According to " Chinese architecture energy consumption research report (2018) ", 2016, Chinese architecture total energy consumption was 8.99
Hundred million tons of standard coals, the 20.6% of Zhan Quanguo total energy consumption;Wherein the year energy consumption level of large public building is common public
1-3 times, 3-4 times of residential architecture of building.And significant portion energy consumption is derived from central air-conditioning system in large public building, because
How this, reduce the important content that the air conditioning energy consumption in public building is China's energy-saving and emission-reduction work.In the design of air-conditioning system
In, the type selecting of air-conditioner host, water pump is determined generally according to the maximum cold of design, thermic load, this causes air-conditioning system most of
Time is under partial load condition and runs, this undoubtedly causes a large amount of energy dissipation.Therefore, it is necessary to central air conditioning
System carries out real-time optimal control, solves the energy waste problem of " low load with strong power ".
Through the literature search of existing technologies, Chinese patent (application) number is 201610017501, entitled " one
The patent of invention of kind of central air conditioning energy-saving control system and its control strategy ", control strategy described in the invention are negative according to room
System regulation is directly instructed in lotus variation, according to the variation calculated room load fluctuation of room temperature, is converted into real-time air quantity and adjusts
Amount, real-time chilled-water flow regulated quantity, real-time cooling water flow regulated quantity, supply backwater temperature difference control model be maintenance system just
The monitoring means often run.The invention is controlled based on the system feedback of load, cannot achieve the Optimization of Energy Saving control of system.In
State's patent (application) number is 03249625, the patent of invention of entitled " energy-saving control device for central ", invention master
To adjust the operating condition of cooling water pump, chilled water pump and blower fan of cooling tower in real time according to user terminal demand by frequency converter, with
Realize the Energy Saving Control of central air-conditioning system.But this Optimization of Energy Saving control device has ignored refrigeration unit operating condition to whole
The energy consumption of a system cannot achieve central air-conditioning system energy saving mesh of overall importance only with the part energy conservation of system for target
Mark, this certainly will reduce its Energy Saving Control effect.Chinese patent (application) number is 200810035560.5, entitled " to be based on model
Central air-conditioning system global optimization energy-saving control method and device " patent of invention, the invention with refrigeration unit, water pump and
Based on the energy consumption model and ARMA Air-conditioning Load Prediction model of blower, each energy consumption equipment is calculated according to computation model
Optimization of Energy Saving operating condition, run whole system under most energy-efficient situation.But there is no consider wind system for the patent of invention
Therefore system energy consumption is said on stricti jurise, can not be known as global optimization Energy Saving Control.In addition, system optimization energy-saving run work
Condition is the specific physical model based on energy consumption component, and there are large errors for physical model and real system, so as to cause system
The failure of Optimization of Energy Saving Controlling model.
Therefore, those skilled in the art is dedicated to developing a kind of central air-conditioning system intelligence based on big data cloud platform
Optimal control method and device, it is therefore intended that overcome the shortcomings of prior art and defect, provide a kind of based on big data cloud platform
Central air-conditioning system intelligent optimized control method and device, utilize the network resources locating technology of current high speed development and big
Data technique realizes multiple and different central air-conditioning system critical component model intelligence learnings and the control of remote online Optimization of Energy Saving,
The human resources of system administration are not only saved, but also the operational energy efficiency of existing central air-conditioning system can also be effectively improved.
Summary of the invention
In view of the above drawbacks of the prior art, the technical problem to be solved by the present invention is to how overcome prior art
Insufficient and defect, provides a kind of central air-conditioning system intelligent optimized control method and device based on big data cloud platform, utilizes
The network resources locating technology and big data technology of current high speed development realize multiple and different central air-conditioning system critical component moulds
Type intelligence learning and the control of remote online Optimization of Energy Saving, had not only saved the human resources of system administration, but also effectively improve existing concentration
The operational energy efficiency of air-conditioning system.
To achieve the above object, the present invention provides a kind of central air-conditioning system intelligent optimizations based on big data cloud platform
Control device, including data transmission module, server data platform, aerial temperature and humidity sensor, air-conditioning box water valve aperture sensing
Device, water temperature sensor, water flow/water flow rate sensor, watt transducer, air-conditioning box Water valve controller, frequency control
Device, refrigeration unit Water temperature control device, the data transmission module include data filtering module, the input of data I/O interface
End, data I/O interface output end, RS485 communication interface, 4G/5G communication interface, WAN communication interface, power supply, data connection end
Mouthful, the output port of the data filtering module is connected with the data I/O interface input terminal, the data I/O interface input
End, data I/O interface output end, RS485 communication interface pass through the data connection port respectively and 4G/5G communication connects
Mouth and the WAN communication interface are connected, the input port of the data filtering module and the aerial temperature and humidity sensor, sky
Adjust the output signal line of case water valve jaw opening sensor, water temperature sensor, water flow/water flow rate sensor, watt transducer
It is respectively connected with, the data I/O interface output end is connected with the input terminal of the air-conditioning box Water valve controller, and the RS485 is logical
Communication interface is connected with the frequency-variable controller, refrigeration unit Water temperature control device, and the 4G/5G communication interface passes through wireless
Network is connected with the server data platform, and the WAN communication interface passes through cable network and the server data platform
It is connected.
Further, the aerial temperature and humidity sensor include surrounding air Temperature Humidity Sensor, air-conditioning box heat exchanger into
Wind aerial temperature and humidity sensor, air-conditioning box heat exchanger outlet air aerial temperature and humidity sensor, air-conditioning box heat exchanger return air temperature
Humidity sensor, the surrounding air Temperature Humidity Sensor are mounted on outdoor, for monitoring surrounding air temperature and humidity, the sky
Case heat exchanger air inlet aerial temperature and humidity sensor is adjusted to be mounted on air-conditioning box heat exchanger air inlet, the air-conditioning box heat exchanger outlet air
Aerial temperature and humidity sensor is mounted on air-conditioning box heat exchanger wind outlet, the air-conditioning box heat exchanger return air temperature and humidity sensing
Device is mounted on air-conditioning box heat exchanger return air duct, and the air-conditioning box heat exchanger air inlet aerial temperature and humidity sensor, air-conditioning box change
The quantity and air-conditioning box number of hot device outlet air aerial temperature and humidity sensor, air-conditioning box heat exchanger return air Temperature Humidity Sensor
Unanimously.
Further, the water temperature sensor includes that refrigeration unit condenser inflow temperature sensor, refrigeration unit are cold
Condenser leaving water temperature sensors, refrigeration unit evaporator inflow temperature sensor, refrigeration unit evaporator leaving water temperature sensing
Device, air-conditioning box inflow temperature sensor, air-conditioning box leaving water temperature sensors, the refrigeration unit condenser inflow temperature sensing
Device and refrigeration unit leaving condenser water temperature sensor are separately mounted in refrigerator condenser inlet and outlet pipes,
The refrigeration unit evaporator inflow temperature sensor and refrigeration unit evaporator leaving water temperature sensors are separately mounted to freeze
In machine evaporator inlet and outlet pipes, the air-conditioning box inflow temperature sensor and air-conditioning box leaving water temperature sensors
It is separately mounted in air-conditioning box heat exchanger inlet and outlet pipes, the refrigeration unit condenser inflow temperature sensor,
Refrigeration unit leaving condenser water temperature sensor, refrigeration unit evaporator inflow temperature sensor, the water outlet of refrigeration unit evaporator
The quantity of temperature sensor is consistent with refrigeration unit quantity, and the air-conditioning box inflow temperature sensor, air-conditioning box leaving water temperature pass
The quantity of sensor is consistent with air-conditioning box number.
Further, the water flow/water flow rate sensor includes chilled water pump water flow/water flow rate sensor, air-conditioning
Case water flow/water flow rate sensor, the chilled water pump water flow/water flow rate sensor are mounted on chilled water pump outlet conduit
On, the air-conditioning box water flow/water flow rate sensor is mounted on air-conditioning box heat exchanger water inlet line, and the chilled water pumps
Flow/water flow rate sensor quantity is consistent with chilled water pump quantity, the number of the air-conditioning box water flow/water flow rate sensor
It measures consistent with air-conditioning box number.
Further, the watt transducer includes blower fan of cooling tower watt transducer, cooling water pump electrical power biography
Sensor, refrigeration unit watt transducer, chilled water pump watt transducer, air-conditioning box blower watt transducer, it is described cold
But tower blower watt transducer, cooling water pump watt transducer, refrigeration unit watt transducer, chilled water pump electric work
Rate sensor, air-conditioning box blower watt transducer are separately mounted to blower fan of cooling tower, cooling water pump, refrigeration unit, chilled water
It pumps, in the power supply line of air-conditioning box blower, the blower fan of cooling tower watt transducer, cooling water pump watt transducer, system
Cold group watt transducer, chilled water pump watt transducer, air-conditioning box blower watt transducer quantity respectively with it is cold
But tower, cooling water pump, refrigeration unit, chilled water pump, air-conditioning box number are consistent.
The control of the present invention also provides a kind of central air-conditioning system intelligent optimal control device based on big data cloud platform
Method processed, the described method comprises the following steps:
Step 1, by aerial temperature and humidity sensor, air-conditioning box water valve jaw opening sensor, water temperature sensor, water flow/water
Flow sensor, watt transducer obtain corresponding data, after data filtering module carries out hardware filtering processing, successively
Server is fed through through 4G/5G communication interface or WAN communication interface by data I/O interface input terminal, data connection port
In data platform;
Data preprocessing procedures are housed, which is advised using filtering method and data in step 2, server data platform
About method pre-processes the data of acquisition;
Step 3 is based on pretreated data, carries out energy to all power-equipments of system using Support vector machine
Consumption energy Model Distinguish, the energy consumption and performance Model Distinguish include refrigeration unit coefficient of performance model, cooling water pump power mould
Type, chilled water pump power module, blower fan of cooling tower power module and air-conditioning box power of fan model, the heat exchange of air-conditioning box heat exchanger
Model;
Step 4, based on step 3 model built, establish and with the minimum optimization aim of air-conditioning system overall energy consumption and protect
The Global Optimization Model for demonstrate,proving the cold demand of user terminal, solves Optimized model using biological evolution algorithm;
Step 5, according to the historical data of refrigeration unit chilled water water-in and water-out temperature and chilled-water flow, utilize autoregression
Sliding average Air-conditioning Load Prediction model obtains future time instance user terminal air-conditioning cold flow demand, the collection then built according to step 4
Middle air-conditioning system Global Optimization Model and Optimized model solver based on biological evolution algorithm obtain system optimization energy conservation fortune
Row operating condition, the system optimization energy-saving run operating condition include blower fan of cooling tower running frequency, cooling water pump running frequency, refrigeration
Unit evaporator is discharged set temperature, each air-conditioning box heat exchanger inlet valve aperture, each air-conditioning box fan operation frequency;
Step 6, each air-conditioning box heat exchanger inlet valve aperture optimal value to pass sequentially through 4G/5G communication interface or WAN logical
Communication interface is fed through in each air-conditioning box Water valve controller through data connection port, data I/O interface output end, meanwhile, each sky
Adjust case fan operation frequency, blower fan of cooling tower running frequency, cooling water pump running frequency, the water outlet setting of refrigeration unit evaporator
The Optimal Parameters value of temperature passes sequentially through 4G/5G communication interface or WAN communication interface respectively, through data connection port and
RS485 communication interface is fed through air-conditioning box fan frequency conversion controller, blower fan of cooling tower frequency-variable controller, cooling water pump frequency conversion control
In device processed, chilled water pump frequency-variable controller and refrigeration unit Water temperature control device, central air-conditioning system global optimization section is realized
It can operation control.
Further, in the step 3 energy consumption and performance Model Distinguish specific descriptions are as follows:
Refrigeration unit coefficient of performancechillerIt is expressed as:
COPchiller=F (tenv,a,φenv,a,ftower,fan,fcooling,wpump,tchilledw,sup,tchilledw,return,
Gchilledw)
In formula, tenv,aFor ambient outdoor air temperature, φenv,aFor ambient outdoor air humidity, ftower,fanFor cooling tower
Blower frequency, fcooling,wpumpFor cooling water pump frequency, tchilledw,supFor evaporator leaving water temperature, tchilledw,returnTo steam
Send out device return water temperature, GchilledwFor evaporator water flow;
Blower fan of cooling tower power Ntower,fanIt is expressed as blower fan of cooling tower frequency ftower,fanFunction, it may be assumed that
Ntower,fan=F (ftower,fan)
Cooling water pump power Ncooling,wpumpIt is expressed as cooling water pump frequency fcooling,wpumpFunction, it may be assumed that
Ncooling,wpump=F (fcooling,wpump)
In the case where level pressure sets operating condition, chilled water pump power Nchilled,wpumpIt is expressed as chilled water pump flow Gchilled,wpump's
Function, it may be assumed that
Nchilled,wpump=F (Gchilled,wpump)
In the case where level pressure sets operating condition, the running frequency of chilled water pump is expressed as chilled water pump flow Gchilled,wpumpLetter
Number, it may be assumed that
fchilled,wpump=F (Gchilled,wpump)
Air-conditioning box power of fan NAHU,fanIt is expressed as air-conditioning box blower frequency fAHU,fanFunction, it may be assumed that
NAHU,fan=F (fAHU,fan)
Air-conditioning box heat exchanger heat exchange amount QAHUIt is expressed as air-conditioning box heat exchanger inlet air temperature tAHU,in,air, air-conditioning box heat exchanger
Enter the wind humidity φAHU,in,air, air-conditioning box blower frequency fAHU,fan, air-conditioning box heat exchanger inflow temperature tAHU,in,waterAnd air-conditioning box
Heat exchanger water flow GAHU,waterFunction:
QAHU=F (tAHU,in,air,φAHU,in,air,fAHU,fan,tAHU,in,water,GAHU,water)
Since the pressure of supply water of chilled water system keeps stablizing, air-conditioning box heat exchanger water valve aperture kAHU,valveIt is expressed as sky
Adjust case heat exchanger water flow GAHU,waterFunction:
kAHU,valve=F (GAHU,water)。
Further, the Optimized model in the step 4 specifically describes are as follows:
Assuming that central air-conditioning system has M platform refrigeration unit, P platform cooling water pump, K platform chilled water pump, J platform cooling tower and R platform
Air-conditioning box operation, then:
Wherein,
Ncooling,wpump,p=F (fcooling,wpump,p) p∈[1,P]
Nchilled,wpump,k=F (Gchilled,wpump,k) k∈[1,K]
Ntower,fan,j=F (ftower,fan,j) j∈[1,J]
NAHU,fan,r=F (fAHU,fan,r) r∈[1,R]
Constraint link formula:
fcooling,wpump,min≤fcooling,wpump,p≤fcooling,wpump,max p∈[1,P]
fchilled,wpump,min≤fchilled,wpump,k≤fchilled,wpump,max k∈[1,K]
fAHU,fan,min≤fAHU,fan,r≤fAHU,fan,max r∈[1,R]
GAHU,water.min≤GAHU,water.r≤GAHU,water.max r∈[1,R]
tchilledw,sup,min≤tchilledw,sup,m≤tchilledw,sup,max m∈[1,M]
QAHU=F (tAHU,in,air,φAHU,in,air,fAHU,fan,tAHU,in,water,GAHU,water)≥QAHU, demand
In formula, subscript " min " is the lower limit value of Optimal Parameters, and subscript " max " is the upper limit value of Optimal Parameters, Qo,demandFor
Air-conditioning total capacity requirement is returned according to the historical data of refrigeration unit chilled water water-in and water-out temperature and chilled-water flow using oneself
Sliding average Air-conditioning Load Prediction model is returned to obtain;QAHU,demandIt is cold according to each air-conditioning box for each air-conditioning box local loading requirements
The historical data for freezing water water-in and water-out temperature and chilled-water flow, is obtained using autoregressive moving average Air-conditioning Load Prediction model
?.
Further, it is particle swarm algorithm, heredity that the biological evolution algorithm in the step 4, which includes optimization algorithm,
Algorithm, differential evolution algorithm, immune algorithm, ant group algorithm, simulated annealing, tabu search algorithm and random search algorithm.
Further, water flow is optimized by each air-conditioning box heat exchanger that the seismic responses calculated obtainsBenefit
With air-conditioning box heat exchanger water valve aperture kAHU,valveWith air-conditioning box heat exchanger water flow GAHU,waterBetween relational expression kAHU,valve
=F (GAHU,water), mapping obtains each air-conditioning box water valve optimization aperture kAHU,valve;Meanwhile it utilizingAnd fchilled,wpump=F (Gchilled,wpump), mapping obtains the optimization fortune of chilled water pump
Line frequency fchilled,wpump。
Advantageous effects of the invention are as follows:
The present invention consider comprehensively each power-equipment of central air-conditioning system (including refrigeration unit, cooling tower, cooling water pump,
Chilled water pump and each air-conditioning box (AHU)) influence of the operating condition to whole system energy consumption, with " global optimization energy conservation " substitution
Current " local optimum energy conservation ", further promotes central air-conditioning system Optimization of Energy Saving effect.Using big data platform and manually
Intelligent algorithm substantially increases the energy consumption model of system dynamic equipment or the precision of performance model, to make Optimized model more
Precisely effectively, meanwhile, higher-dimension Optimized model is solved using biological evolution algorithm, effectively increases optimization computational efficiency,
To realize that the on-line optimization of large-scale centralized air-conditioning system provides necessary condition.Using the network technology of current maturation, number is realized
According to cloud storage and remote transmission, the efficiency of management of central air-conditioning system will be effectively improved, saves a large amount of air-conditioning system pipe
Human resources are managed, to save O&M cost for air-conditioning system administrative department.
Detailed description of the invention
Fig. 1 is the method flow diagram of a preferred embodiment of the invention;
Fig. 2 is the apparatus structure schematic diagram of a preferred embodiment of the invention.
Specific embodiment
Multiple preferred embodiments of the invention are introduced below with reference to Figure of description, keep its technology contents more clear and just
In understanding.The present invention can be emerged from by many various forms of embodiments, and protection scope of the present invention not only limits
The embodiment that Yu Wenzhong is mentioned.
As shown in Figure 1, the present invention by data acquisition, data prediction, based on the power-equipment energy consumption of intelligence learning algorithm
Model Distinguish, the Optimization of Energy Saving condition calculating based on biological evolution algorithm and optimization calculate operating condition and feed back five process compositions, respectively
The main technical schemes of process are discussed below.
One, data acquire:
Using dedicated for serial data being converted to IP data or IP data being converted to serial data, and pass through nothing
What the wireless terminal device (Data Transfer Unit, DTU) of line communication network transmission carried out, i.e., data platform passes through DTU
Module obtains relevant parameter when central air-conditioning system operation, these parameters are obtained by wireless sensor measurement, mainly includes
Blower fan of cooling tower air flow sensor, blower fan of cooling tower electrical power sensor, cooling water pump electrical power sensor, cooling water pump flow pass
Sensor, refrigeration unit condenser inflow temperature, refrigeration unit leaving condenser water temperature, refrigeration unit electrical quantity sensor, refrigeration machine
Group evaporator leaving water temperature sensors, refrigeration unit evaporator return water temperature sensor, chilled water pump electrical power sensor, freezing
Pump capacity sensor, AHU flow of inlet water sensor, AHU inflow temperature sensor, AHU leaving water temperature sensors, AHU air inlet
Temperature-humidity supervising, AHU air-supply temperature-humidity supervising and AHU return air temperature-humidity supervising.
Two, data prediction:
Using data filtering methods (i.e. removal abnormal data) and hough transformation method (i.e. by such as aggregation, deletion redundancy
Feature clusters to reduce the scale of data) data of acquisition are pre-processed, to improve data validity, guarantee high-quality
The subsequent big data learning effect of amount.
Three, the power-equipment energy consumption model identification based on intelligence learning algorithm:
The energy consumption model or performance model of each power-equipment of central air-conditioning system are the bases for realizing system optimization control, are
High-precision power-equipment energy consumption model or performance model are obtained, big data INTELLIGENT IDENTIFICATION technology need to be used.Currently, common intelligence
Energy identification technique mainly has neural network and Support vector machine.Neural network be based on the basis of traditional statistics,
And progressive theory of the content of traditional statistics research when being sample infinity, the i.e. system when sample data tends to be infinite more
Property is counted, and sample data is often limited in practical problem.Compared with neural network, support vector machine method has more
Solid mathematical theory basis, can efficiently solve the High dimensional data model Construct question under the conditions of finite sample, and have
Generalization ability is strong, converges to global optimum, the advantages that dimension is insensitive.Therefore, the invention patent uses Support vector machine
(SVR) on-line identification is carried out to the energy consumption model of each power-equipment of central air-conditioning system, to guarantee the precision of model and reliable
Property, select the gaussian radial basis function (Radial that can handle non-linear relation complicated between input and output variable well
Basis Function, RBF) function as SVR kernel function, according to corresponding input, output data, establishes central air conditioning system
The crucial power-equipment energy consumption model of system or performance model, including refrigeration unit coefficient of performance model, cooling water pump energy consumption model,
Blower fan of cooling tower energy consumption model, chilled water pump energy consumption model, AHU fan energy consumption model and AHU heat exchanger heat exchange models.
Four, based on the Optimization of Energy Saving condition calculating of biological evolution algorithm:
Based on each equipment energy consumption model of system and the coupling incidence relation between them, the central air-conditioning system overall situation is established
Optimization of Energy Saving operating condition model, using biological evolution algorithm (including optimization algorithm be particle swarm algorithm, genetic algorithm, difference
Evolution algorithm, immune algorithm, ant group algorithm, simulated annealing, tabu search algorithm and random search algorithm) to optimization mould
Type is solved, and is obtained central air-conditioning system Optimization of Energy Saving operating condition, is made system in the premise for meeting air conditioner load demand
Under, the total energy consumption of all power-equipments is minimum.
Five, optimization calculates operating condition feedback:
As data acquisition, Optimization of Energy Saving duty parameter is returned to airconditioning control system by DTU module by data platform
System realizes the central air-conditioning system Optimization of Energy Saving control based on cloud service platform.
As shown in Figure 1, control method basic operation process of the present invention is as follows:
The first step, by various sensors (including surrounding air temperature-humidity supervising, air-conditioning box (AHU) heat exchanger import
Air temperature-humidity supervising, air-conditioning box (AHU) heat exchanger exit air temperature-humidity supervising, air-conditioning box (AHU) water valve aperture
Sensor, refrigeration unit condenser inflow temperature sensor, refrigeration unit leaving condenser water temperature sensor, refrigeration unit are steamed
Send out device inflow temperature sensor, refrigeration unit evaporator leaving water temperature sensors, air-conditioning box (AHU) inflow temperature sensor, sky
Adjust case (AHU) leaving water temperature sensors, chilled water pump water flow/water flow rate sensor, air-conditioning box (AHU) water flow/water flow velocity
Sensor, blower fan of cooling tower watt transducer, cooling water pump watt transducer, refrigeration unit watt transducer, freezing
Water pump watt transducer and air-conditioning box (AHU) blower watt transducer) corresponding data is obtained, it is carried out by filter module
After hardware filtering processing, passes sequentially through data I/O interface input terminal, data connection port and 4G/5G communication interface or WAN is logical
Communication interface is fed through in server data platform.
Second step, data preprocessing procedures are equipped in server data platform, which (is removed using filtering method
Abnormal data) and hough transformation method (reducing the scales of data by such as assembling, deleting redundancy feature or cluster) to adopting
The data of collection are pre-processed.
Third step is based on pretreated data, using Support vector machine to all power-equipment energy consumption moulds of system
Type is recognized, including refrigeration unit coefficient of performance model, cooling water pump power module, chilled water pump power module, cooling tower
Power of fan model and air-conditioning box (AHU) power of fan model.
4th step is established based on third step model built with the minimum optimization aim of air-conditioning system overall energy consumption simultaneously
The Global Optimization Model for guaranteeing the cold demand of user terminal, using biological evolution algorithm, (including but not limited to optimization algorithm is particle
Group algorithm, genetic algorithm, differential evolution algorithm, immune algorithm, ant group algorithm, simulated annealing, tabu search algorithm and with
Machine searching algorithm) Optimized model is solved.
5th step is returned according to the historical data of refrigeration unit chilled water water-in and water-out temperature and chilled-water flow using oneself
Sliding average (ARMA) Air-conditioning Load Prediction model is returned to obtain future time instance user terminal air-conditioning cold flow demand, then according to the 4th
The built central air-conditioning system Global Optimization Model of step and the Optimized model solver based on biological evolution algorithm, obtain system
Optimization of Energy Saving operating condition, including the water outlet of blower fan of cooling tower running frequency, cooling water pump running frequency, refrigeration unit evaporator
Set temperature, each air-conditioning box (AHU) heat exchanger inlet valve aperture, each air-conditioning box (AHU) fan operation frequency.
The optimal value of 6th step, each air-conditioning box (AHU) heat exchanger inlet valve aperture passes sequentially through 4G/5G communication interface
Or WAN communication interface, data connection port and data I/O interface output end are fed through each air-conditioning box (AHU) Water valve controller
In, meanwhile, other Optimal Parameters values, including each air-conditioning box (AHU) fan operation frequency, blower fan of cooling tower running frequency, cooling
Water pump operation frequency, refrigeration unit evaporator are discharged set temperature, pass sequentially through 4G/5G communication interface respectively or WAN communication connects
Mouth, data connection port and RS485 communication interface are fed through air-conditioning box (AHU) fan frequency conversion controller, blower fan of cooling tower frequency conversion
In controller, cooling water pump frequency-variable controller, chilled water pump frequency-variable controller and refrigeration unit Water temperature control device, realize
Central air-conditioning system global optimization saving-energy operation control.
As shown in Fig. 2, control method, the present invention provide the central air conditioning based on big data cloud platform to realize the present invention
System intelligent optimal control device, including data transmission module 1 (Data Transfer Unit, DTU), data filtering module
2, data I/O interface input terminal 31, data I/O interface output end 32, RS485 communication interface 4,4G/5G communication interface 5, WAN
Communication interface 6, power supply 7, server data platform 8, data connection port 9, surrounding air temperature-humidity supervising 101, AHU is changed
Hot device inlet air temperature-humidity supervising 102, AHU heat exchanger exit air temperature-humidity supervising 103, air-conditioning box (AHU) water
Valve opening sensor 11, refrigeration unit condenser inflow temperature sensor 121, refrigeration unit leaving condenser water temperature sensor
122, refrigeration unit evaporator inflow temperature sensor 123, refrigeration unit evaporator leaving water temperature sensors 124, air-conditioning box
(AHU) inflow temperature sensor 125, air-conditioning box (AHU) leaving water temperature sensors 126, chilled water pump water flow/water flow velocity pass
Sensor 131, air-conditioning box (AHU) water flow/water flow rate sensor 132, blower fan of cooling tower watt transducer 141, cooling water pump
Watt transducer 142, refrigeration unit watt transducer 143, chilled water pump watt transducer 144, air-conditioning box (AHU)
Blower watt transducer 145, air-conditioning box (AHU) Water valve controller 15, air-conditioning box (AHU) fan frequency conversion controller 16 are cold
But tower fan frequency conversion controller 17, cooling water pump frequency-variable controller 18, chilled water pump frequency-variable controller 19, refrigeration unit supply water
Temperature controller 20.Wherein, data filtering module 2, data I/O interface input terminal 31, data I/O interface output end 32,
RS485 communication interface 4,4G/5G communication interface 5, WAN communication interface 6, power supply 7 and data connection port 9 are placed in data transmission
In module 1.The output port of data filtering module 2 is connected with data I/O interface input terminal 31, data I/O interface input terminal
31, data I/O interface output end 32 and RS485 communication interface 4 pass through data connection port 9 and 4G/5G communication interface 5 respectively
And WAN communication interface 6 is connected, the input port of data filtering module 2 and several air temperature-humidity supervisings (including environment
Air temperature-humidity supervising 101, AHU heat exchanger air inlet/outlet air temperature-humidity supervising 102 and AHU heat exchanger return air
Temperature-humidity supervising 103), several air-conditioning box (AHU) water valve jaw opening sensors 11, several water temperature sensors (including
Refrigeration unit condenser inflow temperature sensor 121, refrigeration unit leaving condenser water temperature sensor 122, refrigeration unit evaporation
Device inflow temperature sensor 123, refrigeration unit evaporator leaving water temperature sensors 124, air-conditioning box (AHU) inflow temperature sensing
Device 125 and air-conditioning box (AHU) leaving water temperature sensors 126), several water flow/water flow rate sensors (including chilled water pump
Water flow/water flow rate sensor 131 and air-conditioning box (AHU) water flow/water flow rate sensor 132) and several electric power sensors
Device (including blower fan of cooling tower watt transducer 141, cooling water pump watt transducer 142, refrigeration unit electric power sensor
Device 143, chilled water pump watt transducer 144 and air-conditioning box (AHU) blower watt transducer 145) output signal line point
Not Xiang Lian, data I/O interface output end 32 is connected with the input terminal of several air-conditioning box (AHU) Water valve controllers 15, RS485
Communication interface 4 and several air-conditioning box (AHU) fan frequency conversion controllers 16, several blower fan of cooling tower frequency-variable controllers 17, if
Dry cooling water pump frequency-variable controller 18, several chilled water pump frequency-variable controllers 19, several refrigeration unit supply water temperature controls
Device 20 processed is connected, and 4G/5G communication interface 5 is connected by wireless network with server data platform 8, and WAN communication interface 6 passes through
Cable network is connected with server data platform 8.
Outdoor mounted has surrounding air temperature-humidity supervising 101, for monitoring surrounding air temperature and humidity, every refrigeration machine
Condenser inlet and outlet pipes are separately installed with refrigeration unit condenser inflow temperature sensor 121 and refrigeration unit
Leaving condenser water temperature sensor 122, every evaporator of refrigerator inlet and outlet pipes are separately installed with refrigeration unit
Evaporator inflow temperature sensor 123 and refrigeration unit evaporator leaving water temperature sensors 124, every chilled water pump outlet pipe
Road is equipped with chilled water pump water flow/water flow rate sensor 131, and every air-conditioning box (AHU) heat exchanger water inlet line installation is free
Adjust case (AHU) water flow/water flow rate sensor 132 and air-conditioning box (AHU) inflow temperature sensor 125, every air-conditioning box
(AHU) heat exchanger outlet conduit is equipped with air-conditioning box (AHU) leaving water temperature sensors 126, every air-conditioning box (AHU) heat exchanger
Air inlet and wind outlet are separately installed with AHU heat exchanger air inlet/outlet air temperature-humidity supervising 102, every air-conditioning box
(AHU) return air duct is equipped with AHU heat exchanger return air temperature-humidity supervising 103, and all power-equipments include in system
Blower fan of cooling tower, cooling water pump, refrigeration unit, chilled water pump and air-conditioning box (AHU) blower power supply line on pacify respectively
Equipped with watt transducer (including blower fan of cooling tower watt transducer 141, cooling water pump watt transducer 142, refrigeration
Unit watt transducer 143, chilled water pump watt transducer 144 and air-conditioning box (AHU) blower watt transducer
145)。
The energy consumption model or coefficient of performance model of each power-equipment of central air-conditioning system are the bases for realizing system optimization control
Plinth.According to equipment operation logic, each power-equipment energy consumption model or coefficient of performance model can be described with formula (1):
N=F (x1,x2,x3…xn) (1)
In formula (1), power N is output parameter, x1,x2,x3…xnIt is input parameter, F representation relation function.
Using Support vector machine (SVR) to the energy consumption model or performance model of each power-equipment of central air-conditioning system
On-line identification is carried out, for the precision and reliability for guaranteeing model, selection can handle complicated between input and output variable well
The gaussian radial basis function (Radial Basis Function, RBF) of non-linear relation function is as SVR kernel function, according to phase
The input answered, output data, establish central air-conditioning system key power-equipment energy consumption model or performance model, including refrigeration machine
Group coefficient of performance model, blower fan of cooling tower energy consumption model, cooling water pump energy consumption model, chilled water pump energy consumption model, AHU blower
Energy consumption model and AHU heat exchanger heat exchange models.In the following, these models are described one by one.
Influence the refrigeration unit coefficient of performance (COPchiller) parameter mainly have: ambient outdoor air temperature (tenv,a), room
External environment air humidity (φenv,a), blower fan of cooling tower frequency (ftower,fan), cooling water pump frequency (fcooling,wpump), evaporation
Device leaving water temperature (tchilledw,sup), evaporator return water temperature (tchilledw,return), evaporator water flow (Gchilledw), therefore,
The refrigeration unit coefficient of performance (COPchiller) can be expressed as:
COPchiller=F (tenv,a,φenv,a,ftower,fan,fcooling,wpump,tchilledw,sup,tchilledw,return,
Gchilledw) (2)
Refrigeration unit leaving condenser water temperature (tcondenserw,out) it is an important safe operation index, it will appear in
In the constraint condition of Optimized model, it can be expressed as:
tcondenserw,out=F (tenv,a,φenv,a,ftower,fan,fcooling,wpump,tchilledw,sup,tchilledw,return,
Gchilledw) (3)
Blower fan of cooling tower power (Ntower,fan) blower fan of cooling tower frequency (f can be expressed astower,fan) function, it may be assumed that
Ntower,fan=F (ftower,fan) (4)
Cooling water pump power (Ncooling,wpump) cooling water pump frequency (f can be expressed ascooling,wpump) function, it may be assumed that
Ncooling,wpump=F (fcooling,wpump) (5)
Since practical chilled water system uses constant DP control, in the case where certain level pressure sets operating condition, chilled water pump power
(Nchilled,wpump) chilled water pump flow (G can be expressed aschilled,wpump) function, it may be assumed that
Nchilled,wpump=F (Gchilled,wpump) (6)
Equally, in the case where certain level pressure sets operating condition, the running frequency of chilled water pump may also indicate that into chilled water pump flow
(Gchilled,wpump) function, it may be assumed that
fchilled,wpump=F (Gchilled,wpump) (7)
AHU power of fan (NAHU,fan) AHU blower frequency (f can be expressed asAHU,fan) function, it may be assumed that
NAHU,fan=F (fAHU,fan) (8)
AHU heat exchanger heat exchange amount (QAHU) AHU heat exchanger inlet air temperature (t can be expressed asAHU,in,air), AHU heat exchanger into
Wind moisture (φAHU,in,air), AHU blower frequency (fAHU,fan), AHU heat exchanger inflow temperature (tAHU,in,water) and AHU heat exchanger
Water flow (GAHU,water) function:
QAHU=F (tAHU,in,air,φAHU,in,air,fAHU,fan,tAHU,in,water,GAHU,water) (9)
Since the pressure of supply water of chilled water system keeps stablizing, AHU heat exchanger water valve aperture (kAHU,valve) can be with
It is expressed as AHU heat exchanger water flow (GAHU,water) function:
kAHU,valve=F (GAHU,water) (10)
In the present embodiment, it is assumed that central air-conditioning system has M platform refrigeration unit, P platform cooling water pump, K platform chilled water pump, J platform
Cooling tower and R platform air-conditioning box (AHU) operation, then central air-conditioning system Optimization of Energy Saving operating condition computation model is described as follows:
Wherein,
Ncooling,wpump,p=F (fcooling,wpump,p) p∈[1,P]
Nchilled,wpump,k=F (Gchilled,wpump,k) k∈[1,K]
Ntower,fan,j=F (ftower,fan,j) j∈[1,J]
NAHU,fan,r=F (fAHU,fan,r) r∈[1,R]
Constraint link formula:
fcooling,wpump,min≤fcooling,wpump,p≤fcooling,wpump,max p∈[1,P] (11a)
fchilled,wpump,min≤fchilled,wpump,k≤fchilled,wpump,max k∈[1,K] (11b)
fAHU,fan,min≤fAHU,fan,r≤fAHU,fan,max r∈[1,R] (11c)
GAHU,water.min≤GAHU,water.r≤GAHU,water.max r∈[1,R] (11d)
tchilledw,sup,min≤tchilledw,sup,m≤tchilledw,sup,max m∈[1,M] (11e)
QAHU=F (tAHU,in,air,φAHU,in,air,fAHU,fan,tAHU,in,water,GAHU,water)≥QAHU, demand (11i)
In formula (11)~(11i), subscript " min " is the lower limit value of Optimal Parameters, and subscript " max " is the upper of Optimal Parameters
Limit value, for example, fcooling,wpump,minRepresent cooling water pump running frequency lower limit value, fcooling,wpump,maxRepresent cooling water pump fortune
Line frequency upper limit value, and so on;Qo,demandIt, can be according to refrigeration unit chilled water water-in and water-out temperature for air-conditioning total capacity requirement
With the historical data of chilled-water flow, obtained using autoregressive moving average (ARMA) Air-conditioning Load Prediction model;QAHU,demand
It, can be according to each air-conditioning box (AHU) chilled water water-in and water-out temperature and chilled-water flow for each air-conditioning box (AHU) local loading requirements
Historical data, utilize autoregressive moving average (ARMA) Air-conditioning Load Prediction model obtain.
Optimized model (11) solve use biological evolution algorithm, including optimization algorithm be particle swarm algorithm, genetic algorithm,
Differential evolution algorithm, immune algorithm, ant group algorithm, simulated annealing, tabu search algorithm and random search algorithm.
Water flow is optimized by each air-conditioning box (AHU) heat exchanger that Optimized model (11) is calculatedThen
According to AHU heat exchanger water valve aperture (kAHU,valve) and AHU heat exchanger water flow (GAHU,water) between relational expression (10), reflect
It penetrates to obtain each air-conditioning box (AHU) water valve optimization aperture (kAHU,valve), meanwhile, according to formula (11f) and formula (7), mapping obtains cold
Freeze the optimization running frequency (f of water pumpchilled,wpump)。
Claims (10)
1. a kind of central air-conditioning system intelligent optimal control device based on big data cloud platform, which is characterized in that including data
Transmission module, server data platform, aerial temperature and humidity sensor, air-conditioning box water valve jaw opening sensor, water temperature sensor, water
Flow/water flow rate sensor, watt transducer, air-conditioning box Water valve controller, frequency-variable controller, refrigeration unit supply water temperature control
Device processed, the data transmission module include data filtering module, data I/O interface input terminal, data I/O interface output end,
RS485 communication interface, 4G/5G communication interface, WAN communication interface, power supply, data connection port, the data filtering module
Output port is connected with the data I/O interface input terminal, the data I/O interface input terminal, data I/O interface output end,
RS485 communication interface passes through the data connection port and the 4G/5G communication interface and the WAN communication interface phase respectively
Even, the input port of the data filtering module and the aerial temperature and humidity sensor, air-conditioning box water valve jaw opening sensor, water temperature
Degree sensor, water flow/water flow rate sensor, watt transducer output signal line be respectively connected with, the data I/O interface
Output end is connected with the input terminal of the air-conditioning box Water valve controller, the RS485 communication interface and the frequency-variable controller, system
Cold group Water temperature control device is connected, and the 4G/5G communication interface passes through wireless network and the server data platform phase
Even, the WAN communication interface is connected by cable network with the server data platform.
2. the central air-conditioning system intelligent optimal control device based on big data cloud platform as described in claim 1, feature
It is, the aerial temperature and humidity sensor includes surrounding air Temperature Humidity Sensor, air-conditioning box heat exchanger air inlet aerial temperature and humidity
Sensor, air-conditioning box heat exchanger outlet air aerial temperature and humidity sensor, air-conditioning box heat exchanger return air Temperature Humidity Sensor, it is described
Surrounding air Temperature Humidity Sensor is mounted on outdoor, and for monitoring surrounding air temperature and humidity, the air-conditioning box heat exchanger air inlet is empty
Temperature and moisture sensor is mounted on air-conditioning box heat exchanger air inlet, the air-conditioning box heat exchanger outlet air aerial temperature and humidity sensor peace
Mounted in air-conditioning box heat exchanger wind outlet, the air-conditioning box heat exchanger return air Temperature Humidity Sensor is mounted on air-conditioning box heat exchanger
On return air duct, the air-conditioning box heat exchanger air inlet aerial temperature and humidity sensor, air-conditioning box heat exchanger outlet air aerial temperature and humidity are passed
Sensor, the quantity of air-conditioning box heat exchanger return air Temperature Humidity Sensor are consistent with air-conditioning box number.
3. the central air-conditioning system intelligent optimal control device based on big data cloud platform as described in claim 1, feature
It is, the water temperature sensor includes refrigeration unit condenser inflow temperature sensor, refrigeration unit leaving condenser water temperature
Sensor, refrigeration unit evaporator inflow temperature sensor, refrigeration unit evaporator leaving water temperature sensors, air-conditioning box water inlet temperature
Spend sensor, air-conditioning box leaving water temperature sensors, the refrigeration unit condenser inflow temperature sensor and refrigeration unit condensation
Device leaving water temperature sensors are separately mounted in refrigerator condenser inlet and outlet pipes, the refrigeration unit evaporator
Inflow temperature sensor and refrigeration unit evaporator leaving water temperature sensors be separately mounted to evaporator of refrigerator water inlet line and
On outlet conduit, the air-conditioning box inflow temperature sensor and air-conditioning box leaving water temperature sensors are separately mounted to air-conditioning box heat exchange
In device inlet and outlet pipes, the refrigeration unit condenser inflow temperature sensor, refrigeration unit leaving condenser water temperature
Spend sensor, refrigeration unit evaporator inflow temperature sensor, the quantity and system of refrigeration unit evaporator leaving water temperature sensors
Cold group quantity is consistent, the air-conditioning box inflow temperature sensor, the quantity of air-conditioning box leaving water temperature sensors and air-conditioning box number
Amount is consistent.
4. the central air-conditioning system intelligent optimal control device based on big data cloud platform as described in claim 1, feature
It is, the water flow/water flow rate sensor includes chilled water pump water flow/water flow rate sensor, air-conditioning box water flow/water flow
Fast sensor, the chilled water pump water flow/water flow rate sensor are mounted on chilled water pump outlet conduit, the air-conditioning box water
Flow/water flow rate sensor is mounted on air-conditioning box heat exchanger water inlet line, the chilled water pump water flow/water flow rate sensor
Quantity it is consistent with chilled water pump quantity, the quantity of the air-conditioning box water flow/water flow rate sensor is consistent with air-conditioning box number.
5. the central air-conditioning system intelligent optimal control device based on big data cloud platform as described in claim 1, feature
It is, the watt transducer includes blower fan of cooling tower watt transducer, cooling water pump watt transducer, refrigeration unit
Watt transducer, chilled water pump watt transducer, air-conditioning box blower watt transducer, the blower fan of cooling tower electrical power
Sensor, cooling water pump watt transducer, refrigeration unit watt transducer, chilled water pump watt transducer, air-conditioning box
Blower watt transducer is separately mounted to blower fan of cooling tower, cooling water pump, refrigeration unit, chilled water pump, air-conditioning box blower
In power supply line, the blower fan of cooling tower watt transducer, cooling water pump watt transducer, refrigeration unit electric power sensor
Device, chilled water pump watt transducer, air-conditioning box blower watt transducer quantity respectively with cooling tower, cooling water pump, system
Cold group, chilled water pump, air-conditioning box number are consistent.
6. the controlling party of the central air-conditioning system intelligent optimal control device based on big data cloud platform as described in claim 1
Method, which is characterized in that the described method comprises the following steps:
Step 1, by aerial temperature and humidity sensor, air-conditioning box water valve jaw opening sensor, water temperature sensor, water flow/water flow velocity
Sensor, watt transducer obtain corresponding data, after data filtering module carries out hardware filtering processing, pass sequentially through number
It is flat to be fed through server data through 4G/5G communication interface or WAN communication interface according to I/O interface input terminal, data connection port
In platform;
Data preprocessing procedures are housed, which uses filtering method and hough transformation method in step 2, server data platform
The data of acquisition are pre-processed;
Step 3 is based on pretreated data, carries out energy consumption and performance to all power-equipments of system using Support vector machine
Model Distinguish, the energy consumption and performance Model Distinguish include refrigeration unit coefficient of performance model, cooling water pump power module, chilled water
Pump power model, blower fan of cooling tower power module and air-conditioning box power of fan model, air-conditioning box heat exchanger heat exchange models;
Step 4, based on step 3 model built, establish and with the minimum optimization aim of air-conditioning system overall energy consumption and guarantee to use
The Global Optimization Model of the cold demand in family end, solves Optimized model using biological evolution algorithm;
Step 5, according to the historical data of refrigeration unit chilled water water-in and water-out temperature and chilled-water flow, slided using autoregression
Average Air-conditioning Load Prediction model obtains future time instance user terminal air-conditioning cold flow demand, then hollow according to the collection that step 4 is built
Adjusting system Global Optimization Model and Optimized model solver based on biological evolution algorithm obtain system optimization energy-saving run work
Condition, the system optimization energy-saving run operating condition include blower fan of cooling tower running frequency, cooling water pump running frequency, refrigeration unit steaming
It sends out device and is discharged set temperature, each air-conditioning box heat exchanger inlet valve aperture, each air-conditioning box fan operation frequency;
Step 6, each air-conditioning box heat exchanger inlet valve aperture optimal value pass sequentially through 4G/5G communication interface or WAN communication connect
Mouthful, it is fed through in each air-conditioning box Water valve controller through data connection port, data I/O interface output end, meanwhile, each air-conditioning box wind
Machine running frequency, blower fan of cooling tower running frequency, cooling water pump running frequency, refrigeration unit evaporator are discharged the excellent of set temperature
Change parameter value, 4G/5G communication interface or WAN communication interface is passed sequentially through respectively, through data connection port and RS485 communication interface
Air-conditioning box fan frequency conversion controller, blower fan of cooling tower frequency-variable controller, cooling water pump frequency-variable controller, chilled water pump is fed through to become
In frequency controller and refrigeration unit Water temperature control device, central air-conditioning system global optimization saving-energy operation control is realized.
7. the controlling party of the central air-conditioning system intelligent optimal control device based on big data cloud platform as claimed in claim 6
Method, which is characterized in that the specific descriptions of energy consumption and performance Model Distinguish in the step 3 are as follows:
Refrigeration unit coefficient of performancechillerIt is expressed as:
COPchiller=F (tenv,a,φenv,a,ftower,fan,fcooling,wpump,tchilledw,sup,tchilledw,return,Gchilledw)
In formula, tenv,aFor ambient outdoor air temperature, φenv,aFor ambient outdoor air humidity, ftower,fanFor blower fan of cooling tower frequency
Rate, fcooling,wpumpFor cooling water pump frequency, tchilledw,supFor evaporator leaving water temperature, tchilledw,returnFor evaporator return water
Temperature, GchilledwFor evaporator water flow;
Blower fan of cooling tower power Ntower,fanIt is expressed as blower fan of cooling tower frequency ftower,fanFunction, it may be assumed that
Ntower,fan=F (ftower,fan)
Cooling water pump power Ncooling,wpumpIt is expressed as cooling water pump frequency fcooling,wpumpFunction, it may be assumed that
Ncooling,wpump=F (fcooling,wpump)
In the case where level pressure sets operating condition, chilled water pump power Nchilled,wpumpIt is expressed as chilled water pump flow Gchilled,wpumpFunction,
That is:
Nchilled,wpump=F (Gchilled,wpump)
In the case where level pressure sets operating condition, the running frequency of chilled water pump is expressed as chilled water pump flow Gchilled,wpumpFunction, it may be assumed that
fchilled,wpump=F (Gchilled,wpump)
Air-conditioning box power of fan NAHU,fanIt is expressed as air-conditioning box blower frequency fAHU,fanFunction, it may be assumed that
NAHU,fan=F (fAHU,fan)
Air-conditioning box heat exchanger heat exchange amount QAHUIt is expressed as air-conditioning box heat exchanger inlet air temperature tAHU,in,air, air-conditioning box heat exchanger air inlet it is wet
Spend φAHU,in,air, air-conditioning box blower frequency fAHU,fan, air-conditioning box heat exchanger inflow temperature tAHU,in,waterWith air-conditioning box heat exchanger water
Flow GAHU,waterFunction:
QAHU=F (tAHU,in,air,φAHU,in,air,fAHU,fan,tAHU,in,water,GAHU,water)
Since the pressure of supply water of chilled water system keeps stablizing, air-conditioning box heat exchanger water valve aperture kAHU,valveIt is expressed as air-conditioning box
Heat exchanger water flow GAHU,waterFunction:
kAHU,valve=F (GAHU,water)。
8. the controlling party of the central air-conditioning system intelligent optimal control device based on big data cloud platform as claimed in claim 6
Method, which is characterized in that the Optimized model in the step 4 specifically describes are as follows:
Assuming that central air-conditioning system has M platform refrigeration unit, P platform cooling water pump, K platform chilled water pump, J platform cooling tower and R platform air-conditioning
Case operation, then:
Wherein,
Ncooling,wpump,p=F (fcooling,wpump,p) p∈[1,P]
Nchilled,wpump,k=F (Gchilled,wpump,k) k∈[1,K]
Ntower,fan,j=F (ftower,fan,j) j∈[1,J]
NAHU,fan,r=F (fAHU,fan,r) r∈[1,R]
Constraint link formula:
fcooling,wpump,min≤fcooling,wpump,p≤fcooling,wpump,max p∈[1,P]
fchilled,wpump,min≤fchilled,wpump,k≤fchilled,wpump,max k∈[1,K]
fAHU,fan,min≤fAHU,fan,r≤fAHU,fan,max r∈[1,R]
GAHU,water.min≤GAHU,water.r≤GAHU,water.max r∈[1,R]
tchilledw,sup,min≤tchilledw,sup,m≤tchilledw,sup,max m∈[1,M]
QAHU=F (tAHU,in,air,φAHU,in,air,fAHU,fan,tAHU,in,water,GAHU,water)≥QAHU, demand
In formula, subscript " min " is the lower limit value of Optimal Parameters, and subscript " max " is the upper limit value of Optimal Parameters, Qo,demandFor air-conditioning
Total capacity requirement is slided according to the historical data of refrigeration unit chilled water water-in and water-out temperature and chilled-water flow using autoregression
Average Air-conditioning Load Prediction model obtains;QAHU,demandFor each air-conditioning box local loading requirements, according to each air-conditioning box chilled water into,
The historical data of leaving water temperature and chilled-water flow is obtained using autoregressive moving average Air-conditioning Load Prediction model.
9. the controlling party of the central air-conditioning system intelligent optimal control device based on big data cloud platform as claimed in claim 6
Method, which is characterized in that the biological evolution algorithm in the step 4 include optimization algorithm be particle swarm algorithm, genetic algorithm,
Differential evolution algorithm, immune algorithm, ant group algorithm, simulated annealing, tabu search algorithm and random search algorithm.
10. the control of the central air-conditioning system intelligent optimal control device based on big data cloud platform as claimed in claim 8
Method, which is characterized in that water flow is optimized by each air-conditioning box heat exchanger that the seismic responses calculated obtainsBenefit
With air-conditioning box heat exchanger water valve aperture kAHU,valveWith air-conditioning box heat exchanger water flow GAHU,waterBetween relational expression kAHU,valve=
F(GAHU,water), mapping obtains each air-conditioning box water valve optimization aperture kAHU,valve;Meanwhile it utilizingAnd fchilled,wpump=F (Gchilled,wpump), mapping obtains the optimization fortune of chilled water pump
Line frequency fchilled,wpump。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910446104.8A CN110220288A (en) | 2019-05-27 | 2019-05-27 | Central air-conditioning system intelligent optimized control method and device based on big data cloud platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910446104.8A CN110220288A (en) | 2019-05-27 | 2019-05-27 | Central air-conditioning system intelligent optimized control method and device based on big data cloud platform |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110220288A true CN110220288A (en) | 2019-09-10 |
Family
ID=67818414
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910446104.8A Pending CN110220288A (en) | 2019-05-27 | 2019-05-27 | Central air-conditioning system intelligent optimized control method and device based on big data cloud platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110220288A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110848896A (en) * | 2019-11-12 | 2020-02-28 | 深圳孚沃德斯科技有限公司 | Intelligent energy-saving control system and method for air conditioner cooling system based on neural network |
CN111219856A (en) * | 2019-12-30 | 2020-06-02 | 上海真聂思楼宇科技有限公司 | Air treatment equipment intelligent optimization group control device and method based on 5G communication |
CN111780384A (en) * | 2020-06-15 | 2020-10-16 | 上海海悦实业发展有限公司 | Central air-conditioning control system |
CN111859625A (en) * | 2020-06-28 | 2020-10-30 | 五邑大学 | Energy-saving control method and device based on big data and storage medium |
CN112413831A (en) * | 2020-11-25 | 2021-02-26 | 中国电力科学研究院有限公司 | Energy-saving control system and method for central air conditioner |
CN112923539A (en) * | 2019-12-05 | 2021-06-08 | 新奥数能科技有限公司 | Operation optimization method and system for air conditioning unit |
CN114110939A (en) * | 2021-09-13 | 2022-03-01 | 上海交通大学 | Comprehensive performance and health assessment device for portable central air conditioning system |
CN114543273A (en) * | 2022-02-28 | 2022-05-27 | 上海交通大学 | Self-adaptive deep learning optimization energy-saving control algorithm for central air conditioner cooling system |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2630717Y (en) * | 2003-07-18 | 2004-08-04 | 戴军 | Energy-saving control device for central air conditioning system |
CN101251291A (en) * | 2008-04-03 | 2008-08-27 | 上海交通大学 | Central air conditioning system global optimization energy-saving control method and device based on model |
CN102012077A (en) * | 2010-12-06 | 2011-04-13 | 北京星达技术开发公司 | Energy-saving control system and control method of central air conditioning freezing station |
CN203837200U (en) * | 2013-10-16 | 2014-09-17 | 嘉日国际集团控股有限公司 | Central air-conditioner overall energy conservation control device |
CN104315673A (en) * | 2014-09-16 | 2015-01-28 | 珠海格力电器股份有限公司 | Central air conditioning fuzzy control system and control method |
CN104566868A (en) * | 2015-01-27 | 2015-04-29 | 徐建成 | Central air-conditioning control system and control method thereof |
CN105546759A (en) * | 2016-01-12 | 2016-05-04 | 重庆大学 | Central air-conditioning energy-saving control system and control strategy thereof |
KR20190035007A (en) * | 2017-09-25 | 2019-04-03 | 엘지전자 주식회사 | Air Conditioner And Control Method Thereof |
CN109798646A (en) * | 2019-01-31 | 2019-05-24 | 上海真聂思楼宇科技有限公司 | A kind of air quantity variable air conditioner control system and method based on big data platform |
-
2019
- 2019-05-27 CN CN201910446104.8A patent/CN110220288A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2630717Y (en) * | 2003-07-18 | 2004-08-04 | 戴军 | Energy-saving control device for central air conditioning system |
CN101251291A (en) * | 2008-04-03 | 2008-08-27 | 上海交通大学 | Central air conditioning system global optimization energy-saving control method and device based on model |
CN102012077A (en) * | 2010-12-06 | 2011-04-13 | 北京星达技术开发公司 | Energy-saving control system and control method of central air conditioning freezing station |
CN203837200U (en) * | 2013-10-16 | 2014-09-17 | 嘉日国际集团控股有限公司 | Central air-conditioner overall energy conservation control device |
CN104315673A (en) * | 2014-09-16 | 2015-01-28 | 珠海格力电器股份有限公司 | Central air conditioning fuzzy control system and control method |
CN104566868A (en) * | 2015-01-27 | 2015-04-29 | 徐建成 | Central air-conditioning control system and control method thereof |
CN105546759A (en) * | 2016-01-12 | 2016-05-04 | 重庆大学 | Central air-conditioning energy-saving control system and control strategy thereof |
KR20190035007A (en) * | 2017-09-25 | 2019-04-03 | 엘지전자 주식회사 | Air Conditioner And Control Method Thereof |
CN109798646A (en) * | 2019-01-31 | 2019-05-24 | 上海真聂思楼宇科技有限公司 | A kind of air quantity variable air conditioner control system and method based on big data platform |
Non-Patent Citations (1)
Title |
---|
艾廷廷等: "《普通高等教育"十三五"规划教材 航空发动机状态监测与故障诊断技术 航空、航天类》", 31 July 2017 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110848896A (en) * | 2019-11-12 | 2020-02-28 | 深圳孚沃德斯科技有限公司 | Intelligent energy-saving control system and method for air conditioner cooling system based on neural network |
CN112923539A (en) * | 2019-12-05 | 2021-06-08 | 新奥数能科技有限公司 | Operation optimization method and system for air conditioning unit |
CN111219856A (en) * | 2019-12-30 | 2020-06-02 | 上海真聂思楼宇科技有限公司 | Air treatment equipment intelligent optimization group control device and method based on 5G communication |
CN111780384A (en) * | 2020-06-15 | 2020-10-16 | 上海海悦实业发展有限公司 | Central air-conditioning control system |
CN111859625A (en) * | 2020-06-28 | 2020-10-30 | 五邑大学 | Energy-saving control method and device based on big data and storage medium |
CN112413831A (en) * | 2020-11-25 | 2021-02-26 | 中国电力科学研究院有限公司 | Energy-saving control system and method for central air conditioner |
CN114110939A (en) * | 2021-09-13 | 2022-03-01 | 上海交通大学 | Comprehensive performance and health assessment device for portable central air conditioning system |
CN114110939B (en) * | 2021-09-13 | 2022-10-11 | 上海交通大学 | Comprehensive performance and health assessment device for portable central air conditioning system |
CN114543273A (en) * | 2022-02-28 | 2022-05-27 | 上海交通大学 | Self-adaptive deep learning optimization energy-saving control algorithm for central air conditioner cooling system |
CN114543273B (en) * | 2022-02-28 | 2022-12-02 | 上海交通大学 | Self-adaptive deep learning optimization energy-saving control algorithm for central air conditioner cooling system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110220288A (en) | Central air-conditioning system intelligent optimized control method and device based on big data cloud platform | |
CN104134100B (en) | A kind of energy-saving management system based on cloud computing | |
CN103062861B (en) | Energy-saving method and system for central air conditioner | |
CN100523635C (en) | Intelligent cluster control system of central air-conditioning | |
CN102541015B (en) | Intelligent energy efficiency control system and method | |
CN102147146B (en) | Digital integrated intelligent control system of central air conditioner | |
CN109028446A (en) | A kind of refrigerating plant room control method based on equipment overall performance model | |
CN201589376U (en) | Central air-conditioning variable water volume and variable air volume whole group-control energy saving system | |
CN102283283B (en) | Intelligentized superficial geothermal energy low-temperature grain storage system | |
CN104075403A (en) | Air-conditioning energy consumption monitoring and diagnosing system and method | |
CN201812187U (en) | Energy management control system for electronic information system machine rooms based on cloud computing | |
CN102367980A (en) | Central air-conditioning multi-dimension integrating optimization control system and method | |
CN201992769U (en) | Digital integrated intelligent control system of central air-conditioner | |
CN105115113B (en) | A kind of central air conditioner room efficiency optimization system | |
CN201014677Y (en) | Central air-conditioning intelligent group control device | |
CN109028447A (en) | A kind of air conditioner refrigerating computer room intelligence control system and control method based on cloud computing | |
CN110895029A (en) | Building load prediction method based on temperature of chilled water | |
CN116857863B (en) | Multi-energy complementary system optimal control method and device based on large-scale ground source heat pump | |
CN109283900B (en) | Building dual water supply and power-assisted water supply energy-saving emission-reduction standardization system and control method | |
CN205137786U (en) | Building power -operated control and subitem measurement system | |
CN105318500A (en) | Building energy resource control and subentry metering system | |
CN202792401U (en) | Intelligent control system for central air-conditioner | |
CN105240993A (en) | Fine energy-saving control system of central air conditioner and achieving method of fine energy-saving control system | |
CN107036231A (en) | Cooling tower intelligent energy-saving control method in central air-conditioning monitoring system | |
CN103528294B (en) | A kind of efficiency processing method of refrigeration system and system |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190910 |
|
RJ01 | Rejection of invention patent application after publication |