CN109059170A - Central air conditioning system based on neural network algorithm - Google Patents
Central air conditioning system based on neural network algorithm Download PDFInfo
- Publication number
- CN109059170A CN109059170A CN201810637098.XA CN201810637098A CN109059170A CN 109059170 A CN109059170 A CN 109059170A CN 201810637098 A CN201810637098 A CN 201810637098A CN 109059170 A CN109059170 A CN 109059170A
- Authority
- CN
- China
- Prior art keywords
- control
- neural network
- central air
- module
- running state
- 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
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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses a kind of central air conditioning systems based on neural network algorithm, including base control unit, system energy efficiency analysis module, neural network learning module, system safety monitoring module, system energy efficiency memory module, control information storage module and system failure memory module, multinomial running state parameter needed for input, output cooling tower electric machine start and stop state, different electric machine frequencies carry out the operation of control system;Input information enters carries out safety detection first after base control unit, judge whether system running state exceeds preset threshold, if passing through safety detection, input information enters neural network learning module, analysis obtains newest control signal, if exceeding preset threshold, the base control unit automatically switches to Traditional control mode.The present invention is capable of the operational efficiency and control parameter of the adaptive central air-conditioning of self study, can adjust the control parameter of air-conditioning system in real time according to changeable influence factor, guarantees system real time execution in efficiency optimization point.
Description
Technical field
The present invention relates to a kind of central air conditioning system more particularly to a kind of central air-conditioning based on neural network algorithm
Control system.
Background technique
" 2013-2017 China's intelligent building industry market prospect and investment strategy planning application are reported " display, China
The total amount of building energy consumption rises year by year, and proportion has been raised to 27.45% in energy aggregate consumption, moves closer to three one-tenth.
And in building energy consumption, the energy consumption of central air-conditioning accounts for about 40%~60% again.Building energy conservation has become most energy-saving potential
Field, and the energy conservation of central air-conditioning is even more the core of building energy conservation.Central air conditioner system can be realized the tune of indoor temperature and humidity
Control, can not only improve comfort level, the cleanliness of room air, also play key to the quality of special process in certain industrial applications
Regulating and controlling effect.Therefore, the operation of central air-conditioning is not only related to building energy conservation, is also relate to building safety and quality of production tune
Control;The control system of central air-conditioning not only needs accurately, it is also desirable to have enough safety assurances.
Central air conditioner system includes refrigeration unit, freezing water circulation system, cooling water recirculation system and air-line system etc., often
The control that the control of rule is mainly recycled, blown with return air and refrigeration unit compressor to chilled water circulation, cooling water.Center
Structure is complicated for air-conditioning system, and component is various, and the control difficulty of system is high.Meanwhile the efficiency of central air conditioner system greatly relies on
In the factors such as outdoor temperature humidity and duration of service, cause that the system effectiveness highest point of central air-conditioning can change in real time shows
As.Fig. 1 illustrates system effectiveness situation of change of the pump type heat central air-conditioning in 1 year, wherein curve 1 is Air temperature
Curve, curve 2 are equipment actual operating efficiency change curve, and curve 3 is equipment optimized operation efficiency curve, it is seen that spring and autumn
Season, system effectiveness was slightly higher, summer with outdoor temperature increase system effectiveness dramatic decrease.In conclusion central air conditioner system
Energy conservation needs a kind of intelligentized control system with self study adaptive ability, can be found according to history data in real time
System energy efficiency highest point, the gap of reduction system actual operating efficiency and optimized operation efficiency.
After nerve network system appears in the 1940s, be by the adjustable connection weight connection of numerous neurons and
At, have the characteristics that MPP, distributed information storage, good self-organizing self-learning capability.Neural network is calculated
Method can theoretically approach arbitrary function, and basic structure is made of nonlinear change unit, have very strong non-linear reflect
Ability is penetrated, flexibility is big, multi-field all with application potential in signal processing, intelligent control, fault diagnosis etc..Based on nerve net
The flexible self study adaptive ability of network system, present invention optimization improve traditional central air conditioning system, can be cleverer
It lives in regulating and controlling central air conditioner system, has greatly saved the energy consumption of central air conditioner system.
Summary of the invention
Technical problem to be solved by the invention is to provide a kind of central air conditioning system based on neural network algorithm,
Can the adaptive central air conditioning system of self study, the control of air-conditioning system can be adjusted in real time according to changeable influence factor
Parameter processed guarantees system real time execution in efficiency optimization point.
The present invention the technical solution adopted is that provides a kind of based on neural network algorithm to solve above-mentioned technical problem
Central air conditioning system, including system failure memory module: join for recording corresponding control when deviation occurs in system control
Several and system running state;
Base control unit: providing Traditional control mode, input the multinomial running state parameter of central air conditioner system, exports
Cooling tower electric machine start and stop state, refrigerating water pump electric machine frequency and cooling pump electric machine frequency control the operation of central air-conditioning;
System energy efficiency memory module: for recording the average coefficient of refrigerating performance of system under set time frequency;
System energy efficiency analysis module: inputting the multinomial running state parameter of central air conditioner system, calculates control signal in real time
System after sending in a period of time is averaged coefficient of refrigerating performance, and calculated result and air-conditioning system running state parameter are collectively stored in
In the system energy efficiency memory module, and it is conveyed to neural network learning module;
Neural network learning module: it is input with system energy efficiency data and system control information, exports in current environment item
The control parameter of the highest operating point of efficiency under part, and give to base control unit;
System safety monitoring module: by will generate control signal and system failure memory module in historical data into
Row compares, and judges whether output control signal or control signal is returned to base control unit;
Control information storage module: for recording the control signal generated each time;
Input information enters carries out safety detection first after base control unit, it is pre- to judge whether system running state exceeds
If threshold value, if system has passed through safety detection, input information enters neural network learning module, and analysis obtains newest control
Signal, if system operation exceeds preset threshold, the base control unit automatically switches to Traditional control mode.
The above-mentioned central air conditioning system based on neural network algorithm, wherein the central air conditioner system it is multinomial
Running state parameter includes: the water temperature and pressure at water temperature and pressure, condenser at refrigeration unit evaporator, and indoor and outdoor is warm and humid
Electric current and the load of degree and each motor.
The above-mentioned central air conditioning system based on neural network algorithm, wherein the Traditional control mode uses PID
Refrigerating water pump electric machine frequency and cooling pump electric machine frequency are adjusted, cooling tower electric machine start and stop state is controlled by PLC.
The above-mentioned central air conditioning system based on neural network algorithm, wherein the system safety monitoring module: logical
It crosses and is compared with the abnormality point recorded in system failure memory module, evade abnormal control signal in advance;If safety inspection
Survey passes through, and control signal is exported to system equipment, if safety detection does not pass through, base control unit is returned, uses tradition
PID and PLC control.
The above-mentioned central air conditioning system based on neural network algorithm, wherein in initial operating stage, first to central air-conditioning
Carry out artificial regulatory, during manual debugging, by control information storage module constantly record air-conditioning system operation and
Control information;The neural network learning module receives system energy efficiency memory module and controls the data of information storage module accumulation
Amount constantly carries out debugging study, and the data volume that system energy efficiency memory module and control information storage module accumulate reaches preset threshold
Afterwards, restart neural network learning module and output control signals to base control unit.
The above-mentioned central air conditioning system based on neural network algorithm, wherein the central air conditioner system includes system
Cold group, freezing water circulation system, cooling water recirculation system and air-line system, the refrigeration unit are completed to freeze by evaporator
Agent and the cooling capacity of chilled water or heat exchange, and cooling capacity or heat transfer to indoor return air, are passed through air hose system by subsequent chilled water
System completes the control to indoor temperature and humidity;The cooling water recirculation system receives the heat that refrigeration unit condenser generates, finally
Evaporative heat loss is completed at cooling tower.
The above-mentioned central air conditioning system based on neural network algorithm, wherein the operating status that factory acquires on the spot
Parameter is by wired with the transmission mode metering-in control system wirelessly combined;The wired data transfer mode uses RS-
485 agreements provide differential signal by both threads, realize required remote, high rate data transmission;The wireless data transmission
Remote transmission is carried out by the way of WIFI or 4G.
The present invention comparison prior art has following the utility model has the advantages that the center provided by the invention based on neural network algorithm
Air-conditioner control system, using the adaptive feature of the self study of neural network algorithm in computer science, in conjunction with traditional control
Logic can make control system constantly analyze, store, learn the operation characteristic of a certain specific central air-conditioning system, and then control
Air-conditioning system real time execution is at system effectiveness highest point.The present invention not only can greatly reduce the cost and difficulty of artificial O&M
Degree also has high flexibility, can greatly save the annual power consumption of central air conditioner system.
Detailed description of the invention
Fig. 1 is that the operational efficiency of central air conditioning system changes schematic diagram;
Fig. 2 is the configuration diagram of central air conditioning system of the invention;
Control logic figure when Fig. 3 is system debug in the early stage of the invention;
Fig. 4 is control logic figure of the present invention in commencement of commercial operation.
Specific embodiment
The invention will be further described with reference to the accompanying drawings and examples.
Fig. 2 is the configuration diagram of central air conditioning system of the invention;Fig. 4 is control of the present invention in commencement of commercial operation
Logic chart processed.
Refer to Fig. 2 and Fig. 4, the central air conditioning system provided by the invention based on neural network algorithm, Neng Gougen
Constantly learn according to the history data of central air-conditioning, find efficiency optimization point under different operating conditions, in real time to central hollow
Control parameter is adjusted to be fed back and optimized, and further according to the optimum efficiency point of the information look-ahead systems such as following weather
And optimal control parameter.The present invention suitable for industry, the central air conditioner system commercial building, Learning Algorithm from
Learning ability can make system real time execution in best efficiency point, achieve the effect that energy-saving and emission-reduction.
Control system of the invention is divided into multiple control modules, including base control unit, neural network learning module, control
Information storage module, system energy efficiency analysis module, system energy efficiency memory module, system failure memory module and system processed are supervised safely
Survey module;It can record in real time, the efficiency highest point of prediction central air conditioner system, while guarantee the safety and stability of system
Operation, by the logical connection between each submodule, which can effectively improve the real-time of central air conditioner system
Operational energy efficiency.The present invention can not only be also equipped with certain safety guarantee by history data self study efficiency optimization point
Control can switch to automatically legacy system control logic when neural network learning module, which calculates, relatively large deviation, guarantee control
The temperature in region is in permissible range, guarantees the good operation of system equipment.
This control system needs the multinomial running state parameter of central air conditioner system as input, evaporates comprising refrigeration unit
Electric current, the load etc. of water temperature and pressure at device, condenser, indoor and outdoor temperature and humidity and each motor.Control system receives input letter
It can be passed the information on after number to system energy efficiency analysis module and base control unit, be analyzed obtained in system energy efficiency analysis module
As a result system energy efficiency memory module will be stored in.Input information enters carries out safety detection first after base control unit, sentence
Whether disconnected system running state has exceeded the certain threshold values manually set, if system has passed through safety detection, inputs information meeting
Into neural network learning module, analysis obtains newest control signal, if system operation has exceeded certain specific thresholds, is
System can switch to traditional control logic automatically, guarantee the reliable and stable operation of system.
This control system possesses system failure memory module simultaneously, is able to record the running abnormality point of system.When
After above-mentioned control signal generates, system safety monitoring module can be entered, compared by the abnormality point recorded with system,
It is abnormal to further confirm that the signal of output will not be such that system generates, evades possible abnormal control signal in advance.If safety detection
Pass through, control signal can be output to system equipment, if safety monitoring does not pass through, system can return to base control unit, use
Traditional control logic.The output control parameter of this system includes: cooling tower electric machine start and stop state, refrigerating water pump electric machine frequency and cold
But pump motor frequency.
In this control system, system energy efficiency analysis module can be calculated in real time after control signal issues is in a period of time
It unites average COP (coefficient of refrigerating performance), calculated result can be collectively stored in system energy efficiency storage mould with air-conditioning system running state parameter
Block.Neural network learning module can be simultaneously input with system energy efficiency data and system control information, export in current environment item
The control parameter of the highest operating point of efficiency under part.
Control logic figure when Fig. 3 is system debug in the early stage of the invention.In the debugging of system initial stage, neural network model
Due to lacking learning experience and learning data, tend not to fine to control central air conditioner system.Therefore, this control system is being transported
Row initial stage, it is still desirable to which technical staff carries out live manual debugging.During manual debugging, each number of this control system
The operation and control information of air-conditioning system can be constantly recorded according to memory module.Control system needs the artificial data volume for determining accumulation
Whether neural network learning module is started enough, and field technician can determine to control according to the study situation of neural network module
The debugging process of system processed.
Traditional control mode of the invention can adjust refrigerating water pump electric machine frequency and cooling pump electric machine frequency using PID, lead to
Cross PLC control cooling tower electric machine start and stop state.The central air conditioner system includes refrigeration unit, freezing water circulation system, cooling
Water circulation system and air-line system, the refrigeration unit complete the cooling capacity of refrigerant and chilled water or the friendship of heat by evaporator
It changes, cooling capacity or heat transfer to indoor return air, are completed the control to indoor temperature and humidity by air-line system by subsequent chilled water;Institute
It states cooling water recirculation system and receives the heat that refrigeration unit condenser generates, evaporative heat loss is finally completed at cooling tower;To
Air quantity intelligentized control method is realized under Traditional control mode, when avoiding being switched to the control signal of neural network learning module offer
Big switch disturbance is caused, so that system switching is more steady.
Present invention running state parameter needed for intelligent control, using wired with the transmission side data wirelessly combined
Formula, not only can guarantee the reliability of data transmission, but also can guarantee stability, so very big that avoid building site environment, noise to data biography
The influence of transmission quality.The wired data transfer mode uses RS-485 agreement, provides differential signal by both threads, realizes
Required remote, high rate data transmission;Wireless data transmission carries out remote transmission by the way of WIFI or 4G.
Although the present invention is disclosed as above with preferred embodiment, however, it is not to limit the invention, any this field skill
Art personnel, without departing from the spirit and scope of the present invention, when can make a little modification and perfect therefore of the invention protection model
It encloses to work as and subject to the definition of the claims.
Claims (7)
1. a kind of central air conditioning system based on neural network algorithm characterized by comprising
System failure memory module: for recording corresponding control parameter and system running state when deviation occurs in system control;
Base control unit: providing Traditional control mode, inputs the multinomial running state parameter of central air conditioner system, output cooling
Tower motor start and stop state, refrigerating water pump electric machine frequency and cooling pump electric machine frequency control the operation of central air-conditioning;
System energy efficiency memory module: for recording the average coefficient of refrigerating performance of system under set time frequency;
System energy efficiency analysis module: inputting the multinomial running state parameter of central air conditioner system, calculates control signal in real time and issues
The system in a period of time is averaged coefficient of refrigerating performance afterwards, calculated result and air-conditioning system running state parameter is collectively stored in described
In system energy efficiency memory module, and it is conveyed to neural network learning module;
Neural network learning module: it is input with system energy efficiency data and system control information, exports under current environmental condition
The control parameter of the highest operating point of efficiency, and give to base control unit;
System safety monitoring module: by comparing the control signal generated with the historical data in system failure memory module
It is right, judge whether output control signal or control signal is returned into base control unit;
Control information storage module: for recording the control signal generated each time;
Input information enters carries out safety detection first after base control unit, judge whether system running state exceeds default threshold
Value, if system has passed through safety detection, input information enters neural network learning module, and analysis obtains newest control letter
Number, if system operation exceeds preset threshold, the base control unit automatically switches to Traditional control mode.
2. as described in claim 1 based on the central air conditioning system of neural network algorithm, which is characterized in that the center
The multinomial running state parameter of air-conditioning system include: water temperature at refrigeration unit evaporator and the water temperature at pressure, condenser with
Pressure, the electric current and load of indoor and outdoor temperature and humidity and each motor.
3. as claimed in claim 2 based on the central air conditioning system of neural network algorithm, which is characterized in that the tradition
Control model adjusts refrigerating water pump electric machine frequency and cooling pump electric machine frequency using PID, controls cooling tower electric machine start and stop shape by PLC
State.
4. as described in claim 1 based on the central air conditioning system of neural network algorithm, which is characterized in that the system
Safety monitoring module evades exception control by comparing with the abnormality point recorded in system failure memory module in advance
Signal;If safety detection passes through, control signal is exported to system equipment, if safety detection does not pass through, returns to base control
Unit is controlled using traditional PID and PLC.
5. as claimed in claim 4 based on the central air conditioning system of neural network algorithm, which is characterized in that first in operation
Phase first carries out artificial regulatory to central air-conditioning, during manual debugging, constantly records sky by controlling information storage module
The operation and control information of adjusting system;The neural network learning module receives system energy efficiency memory module and control information storage
The data volume of module accumulation constantly carries out debugging study, the data of system energy efficiency memory module and control information storage module accumulation
After amount reaches preset threshold, restarts neural network learning module and output control signals to base control unit.
6. as described in claim 1 based on the central air conditioning system of neural network algorithm, which is characterized in that the center
Air-conditioning system includes that refrigeration unit, freezing water circulation system, cooling water recirculation system and air-line system, the refrigeration unit pass through
Evaporator completes exchanging for refrigerant and the cooling capacity of chilled water or heat, and subsequent chilled water returns cooling capacity or heat transfer to indoor
Wind completes the control to indoor temperature and humidity by air-line system;The cooling water recirculation system receives refrigeration unit condenser and produces
Raw heat finally completes evaporative heat loss at cooling tower.
7. as claimed in claim 2 based on the central air conditioning system of neural network algorithm, which is characterized in that factory is on the spot
The running state parameter of acquisition is by wired with the transmission mode metering-in control system wirelessly combined;The cable data passes
Defeated mode uses RS-485 agreement, provides differential signal by both threads, realizes required remote, high rate data transmission;It is described
Wireless data transmission carries out remote transmission by the way of WIFI or 4G.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810637098.XA CN109059170A (en) | 2018-06-20 | 2018-06-20 | Central air conditioning system based on neural network algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810637098.XA CN109059170A (en) | 2018-06-20 | 2018-06-20 | Central air conditioning system based on neural network algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109059170A true CN109059170A (en) | 2018-12-21 |
Family
ID=64821072
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810637098.XA Pending CN109059170A (en) | 2018-06-20 | 2018-06-20 | Central air conditioning system based on neural network algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109059170A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110471380A (en) * | 2019-08-15 | 2019-11-19 | 四川长虹电器股份有限公司 | A kind of air conditioning failure monitoring and method for early warning for smart home system |
CN111538233A (en) * | 2020-05-06 | 2020-08-14 | 上海雁文智能科技有限公司 | Central air conditioner artificial intelligence control method based on energy consumption reward |
CN113601806A (en) * | 2021-06-29 | 2021-11-05 | 无锡有孚精工科技有限公司 | Gas liquid cooling device, system and method for mold production |
CN114279235A (en) * | 2021-12-29 | 2022-04-05 | 博锐尚格科技股份有限公司 | Cooling tower operation control method based on switching of black box model and gray box model |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202040938U (en) * | 2011-01-17 | 2011-11-16 | 福建成信绿集成有限公司 | Central air conditioning equipment energy consumption monitoring and energy conservation diagnosis system |
CN102866643A (en) * | 2012-09-18 | 2013-01-09 | 苏州市新瑞奇节电科技有限公司 | Intelligent energy-saving system based on internet of things |
CN103322647A (en) * | 2013-06-13 | 2013-09-25 | 浙江工业大学 | Predictive control method for supply water temperature of cooling water of central air-conditioner |
CN203824002U (en) * | 2014-04-11 | 2014-09-10 | 杭州哲达科技股份有限公司 | Optimal control system for comprehensive electricity unit consumption of refrigeration station for central air conditioner |
CN106765932A (en) * | 2016-12-14 | 2017-05-31 | 深圳达实智能股份有限公司 | The Energy Efficiency Ratio Forecasting Methodology and device of central air conditioner system refrigeration host computer |
CN107044710A (en) * | 2016-12-26 | 2017-08-15 | 深圳达实智能股份有限公司 | Energy-saving control method for central air conditioner and system based on joint intelligent algorithm |
CN107860102A (en) * | 2017-10-18 | 2018-03-30 | 深圳市中电电力技术股份有限公司 | A kind of method and device for controlling central air-conditioning |
WO2018092258A1 (en) * | 2016-11-18 | 2018-05-24 | 三菱電機株式会社 | Air conditioner and air-conditioning system |
-
2018
- 2018-06-20 CN CN201810637098.XA patent/CN109059170A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202040938U (en) * | 2011-01-17 | 2011-11-16 | 福建成信绿集成有限公司 | Central air conditioning equipment energy consumption monitoring and energy conservation diagnosis system |
CN102866643A (en) * | 2012-09-18 | 2013-01-09 | 苏州市新瑞奇节电科技有限公司 | Intelligent energy-saving system based on internet of things |
CN103322647A (en) * | 2013-06-13 | 2013-09-25 | 浙江工业大学 | Predictive control method for supply water temperature of cooling water of central air-conditioner |
CN203824002U (en) * | 2014-04-11 | 2014-09-10 | 杭州哲达科技股份有限公司 | Optimal control system for comprehensive electricity unit consumption of refrigeration station for central air conditioner |
WO2018092258A1 (en) * | 2016-11-18 | 2018-05-24 | 三菱電機株式会社 | Air conditioner and air-conditioning system |
CN106765932A (en) * | 2016-12-14 | 2017-05-31 | 深圳达实智能股份有限公司 | The Energy Efficiency Ratio Forecasting Methodology and device of central air conditioner system refrigeration host computer |
CN107044710A (en) * | 2016-12-26 | 2017-08-15 | 深圳达实智能股份有限公司 | Energy-saving control method for central air conditioner and system based on joint intelligent algorithm |
CN107860102A (en) * | 2017-10-18 | 2018-03-30 | 深圳市中电电力技术股份有限公司 | A kind of method and device for controlling central air-conditioning |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110471380A (en) * | 2019-08-15 | 2019-11-19 | 四川长虹电器股份有限公司 | A kind of air conditioning failure monitoring and method for early warning for smart home system |
CN111538233A (en) * | 2020-05-06 | 2020-08-14 | 上海雁文智能科技有限公司 | Central air conditioner artificial intelligence control method based on energy consumption reward |
CN113601806A (en) * | 2021-06-29 | 2021-11-05 | 无锡有孚精工科技有限公司 | Gas liquid cooling device, system and method for mold production |
CN114279235A (en) * | 2021-12-29 | 2022-04-05 | 博锐尚格科技股份有限公司 | Cooling tower operation control method based on switching of black box model and gray box model |
CN114279235B (en) * | 2021-12-29 | 2024-05-10 | 博锐尚格科技股份有限公司 | Cooling tower operation control method based on switching of black box model and ash box model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109059170A (en) | Central air conditioning system based on neural network algorithm | |
CN104134100B (en) | A kind of energy-saving management system based on cloud computing | |
CN102367980B (en) | Central air-conditioning multi-dimension integrating optimization control system and method | |
CN108386972B (en) | Energy-saving control system and method for air conditioner of machine room | |
CN102338448B (en) | High-efficiency energy-saving control system for central air conditioner of large-sized supermarket | |
CN202648063U (en) | Central air-conditioner energy efficiency optimization control and management system | |
CN113446705B (en) | Energy-saving control system and control method for subway efficient machine room | |
CN101738944B (en) | Energy-saving control system and energy-saving alarming processing unit integrated with same | |
CN105444356A (en) | Intelligent energy efficiency optimizing control system for central air conditioning system and control method of intelligent energy efficiency optimizing control system | |
CN106765860B (en) | A kind of control system and method for nuclear power station central air-conditioning | |
CN203869259U (en) | Variable pressure difference control device based on openness of chilled water valve of tail-end air conditioning equipment | |
CN109976419B (en) | Automatic control system and method for temperature and pressure reduction of regional cooling and heating steam | |
CN112503746A (en) | Control method of cold source system of power station house based on machine learning and particle swarm algorithm | |
CN110940061A (en) | Central air conditioner control method and system | |
CN114264045A (en) | Energy efficiency regulation and control system and method for central air conditioner | |
CN106885350A (en) | A kind of air conditioner energy conservation control system | |
CN212720195U (en) | Cooling water system control device based on system overall energy efficiency ratio COP is best | |
CN109028447A (en) | A kind of air conditioner refrigerating computer room intelligence control system and control method based on cloud computing | |
CN114659237B (en) | Air conditioner energy efficiency supervision method based on Internet of things | |
CN116255716A (en) | Central air conditioner artificial intelligent load prediction energy-saving strategy | |
CN203464410U (en) | Energy-saving device for controlling heating and cooling of central air conditioner | |
CN104061707A (en) | Intelligent multi-source refrigerating system and intelligent multi-source refrigeration control method | |
CN202675533U (en) | Intelligent control device for central air conditioner | |
CN109307351A (en) | A kind of efficient synthesis energy saving control system for heat pump | |
CN113218040A (en) | Energy efficiency improvement control method for central air-conditioning 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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181221 |
|
WD01 | Invention patent application deemed withdrawn after publication |