CN109341010A - A kind of electric refrigerating machine air-conditioning system energizes integrated control method and device - Google Patents
A kind of electric refrigerating machine air-conditioning system energizes integrated control method and device Download PDFInfo
- Publication number
- CN109341010A CN109341010A CN201811091228.0A CN201811091228A CN109341010A CN 109341010 A CN109341010 A CN 109341010A CN 201811091228 A CN201811091228 A CN 201811091228A CN 109341010 A CN109341010 A CN 109341010A
- Authority
- CN
- China
- Prior art keywords
- preset
- refrigerating machine
- integrated control
- electric refrigerating
- conditioning system
- 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.)
- Granted
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
- 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
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/61—Control or safety arrangements characterised by user interfaces or communication using timers
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The embodiment of the invention discloses a kind of electric refrigerating machine air-conditioning systems to energize integrated control method and device, this method comprises: regularly sending using the refrigeration duty demand result in the following preset duration of preset load prediction neural network model output as emulation input condition to preset Dynamic Simulation Model；Wherein the input parameter of load prediction neural network model includes the current operating data for energizing end；Emulation is optimized by Dynamic Simulation Model to optimize to preset optimized variable；Optimized variable after optimization is issued to the refrigeration system with energy end, and refrigeration system operation is controlled by the optimized variable after optimization.Pass through the example scheme, it realizes energy supply end and is organically coupled integrally with energy end, both it ensure that with the dynamic power distribution equilibrium and comfort requirement under the conditions of the different load of energy end, the Best Economy operation at energy supply end is also ensured, to reduce energy supply end and the O&M cost with energy end.
Description
Technical field
The present embodiments relate to fluid machinery and Heating,Ventilating and Air Conditioning technical field, espespecially a kind of electric refrigerating machine air-conditioning system is used
Energize integrated control method and device.
Background technique
In the central cooling of traditional garden rank, exist with energy supplying system and significantly isolate, with energy end and energy supply end point
Belong to different main bodys, be responsible for the adjusting of air-conditioning system inside building with energy end, the control of refrigeration system, the two are responsible in energy supply end
Separation be building freeze supply mains's interface.What although chilled water was connected to, control information and with energy information by
It interrupts, forms extensive cooling supply management mode, cause the waste of the energy.
Often there is the unbalanced phenomenon of waterpower with energy end, causes building inside least favorable circuit that can not obtain enough cold
Amount, and user often lacks the experience that hydraulic equilibrium adjusts aspect, it can only be by complaining energy supply end to seek to solve.Energize end often
Direct intervention cannot be carried out to building inside hydraulic equilibrium without permission or due to division of duty again, then move back and ask it
It is secondary to be solved by way of increasing chilled-water flow.This just necessarily causes chilled water supply backwater temperature difference to reduce, and increases confession
The power consumption at energy end, reduces the system COP (coefficient of performance cycle performance coefficient) at energy supply end.
Even if energy supply end, which has permission, carries out the adjusting of chilled water system hydraulic equilibrium to building inside, Static Water can only be also carried out
Dynamic balance is adjusted, this is also not suitable for for the currently cold supply system of the amount of generalling use regulative mode.Even if being pressed using dynamic
Poor balanced valve, when loop traffic exceeds valve normal range of operation, hydraulic equilibrium regulatory function can also fail.This external differential is simultaneously
It cannot directly reflect that the actual load demand of user side, customer charge more intuitively show as the variation of the temperature difference.
For different environmental parameters, and with can end room temperature, relative humidity situation, chilled water supply water temperature exists
Certain adjusting space.The power consumption that chilled water supply water temperature can be substantially reduced refrigeration system is improved, but if energy supply end
The above parameter can not be obtained in real time, also just can not supply integrated Energy Saving Control regulating measure using using, it can only be with lower
Supply water temperature operation guarantee with can end cooling supply comfort, cause unnecessary energy waste.It is this to use energy end and confession
The phenomenon that energy end is isolated out is very universal, has been also directly result in the high status of building energy consumption.
Although proposing new control method in terms of dynamic hydraulic equilibrium adjusting and indoor humidity control in recent years,
It is still without a kind of control method by both technological incorporation together, to fundamentally solve the on-demand of building air-conditioner
Energy supply and comfort guarantee.
Summary of the invention
The embodiment of the invention provides a kind of electric refrigerating machine air-conditioning systems to energize integrated control method and device, energy
End, which will enough be energized, and organically coupled with energy end integrally both guarantees to use the dynamic power distribution under the conditions of the different load of energy end equal
Weighing apparatus and comfort requirement, also guarantee energy supply end Best Economy operation, thus reduce energy supply end and with energy end O&M at
This.
In order to reach purpose of the embodiment of the present invention, the embodiment of the invention provides a kind of energy supplies of electric refrigerating machine air-conditioning system
Integrated control method, which comprises
Using preset load prediction neural network model output the following preset duration in refrigeration duty demand result as
Input condition is emulated, is regularly sent to preset Dynamic Simulation Model；Wherein, the input of the load prediction neural network model
Parameter includes the current operating data for energizing end；
Emulation is optimized by the Dynamic Simulation Model, to optimize to preset optimized variable；
The optimized variable after optimization is issued to the refrigeration system with energy end, and is become by the optimization after optimization
Amount controls the refrigeration system operation.
Optionally, the refrigeration duty demand in the following preset duration for exporting preset load prediction neural network model
As a result it as emulation input condition, regularly sends to before preset Dynamic Simulation Model, the method also includes:
Collect the operation data at the energy supply end；The operation data includes the current operating data and history run number
According to；
The load prediction neural network model is trained using the operation data as training set.
Optionally, the operation data includes any of the following or a variety of: outdoor temperature, outside relative humidity, wind speed,
Wind direction, illuminance and refrigeration duty.
Optionally, the input parameter of the load prediction neural network model further include: preset economic index；
The preset economic index includes one or more of: cooling supply price, electricity rates and with water price lattice.
Optionally, the optimized variable includes any of the following or a variety of: cold starts number of units, cooling tower firing platform
Number, cooling water flow, chilled-water flow and chilled water supply water temperature.
Optionally, the method also includes: during being optimized to preset optimized variable, it then follows preset constraint item
Part；
The constraint condition includes any of the following or a variety of: cold maximum refrigerating capacity, cold minimum chilled water flow
Amount, cold minimum cooling water flow, cold maximum chilled-water flow, cold maximum cooling water flow, chilled water pump range of flow,
Cooling water pump range of flow and indoor maximum relative humidity.
Optionally, described to pass through the Dynamic Simulation Model when the optimized variable is the chilled water supply water temperature
Emulation is optimized, includes: to be optimized to preset optimized variable
Using the indoor maximum relative humidity as the constraint condition, by preset in the Dynamic Simulation Model
Optimization algorithm, the highest chilled water supply water temperature currently allowed according to relative humidity calculation maximum in the user room fed back.
Optionally, the Dynamic Simulation Model includes any of the following or a variety of: electric refrigerating machine model, water pump model,
Cooling tower model and resistance of pipe system model.
Optionally, the method also includes: according to the return water temperature and/or the temperature difference on waterpower loop, judge the waterpower
Whether the cooling capacity that chilled water is supplied in loop matches with energy end load demand；
Wherein, when the return water temperature and the temperature difference are equal to setting value, determine chilled water institute in the waterpower loop
The cooling capacity of supply is matched with described with energy end load demand；When the return water temperature and the temperature difference are not equal to setting value,
Determine the cooling capacity and the energy end load demand mismatch that chilled water is supplied in the waterpower loop.
The embodiment of the invention also provides a kind of electric refrigerating machine air-conditioning systems to energize integrated control device, including place
Device and computer readable storage medium are managed, is stored with instruction in the computer readable storage medium, which is characterized in that when described
When instruction is executed by the processor, realize that electric refrigerating machine air-conditioning system described in above-mentioned any one energizes integrated control
Method processed.
The embodiment of the present invention includes: it will be cold in the following preset duration of preset load prediction neural network model output
Workload demand result is regularly sent as emulation input condition to preset Dynamic Simulation Model；Wherein, the load prediction mind
Input parameter through network model includes the current operating data for energizing end；It is optimized by the Dynamic Simulation Model imitative
Very, to be optimized to preset optimized variable；The optimized variable after optimization is issued to the refrigeration system with energy end, and
The refrigeration system operation is controlled by the optimized variable after optimization.By the example scheme, end will be energized by realizing
With with can end organically couple integrally both ensure that with can the dynamic power under the conditions of end different load distribute equilibrium and easypro
Adaptive requirement, also ensures the Best Economy operation at energy supply end, to reduce energy supply end and the O&M cost with energy end.
The other feature and advantage of the embodiment of the present invention will illustrate in the following description, also, partly from explanation
It is become apparent in book, or understand through the implementation of the invention.The objectives and other advantages of the invention can be by illustrating
Specifically noted structure is achieved and obtained in book, claims and attached drawing.
Detailed description of the invention
Attached drawing is used to provide to further understand technical solution of the present invention, and constitutes part of specification, with this
The embodiment of application technical solution for explaining the present invention together, does not constitute the limitation to technical solution of the present invention.
Fig. 1 is that the electric refrigerating machine air-conditioning system of the embodiment of the present invention energizes integrated control method flow chart；
Fig. 2 is the load prediction neural network model schematic of the embodiment of the present invention；
Fig. 3 is the Dynamic Simulation Model structural schematic diagram of the embodiment of the present invention；
Fig. 4 is the information flow model schematic diagram of the embodiment of the present invention；
Fig. 5 is that the electric refrigerating machine air-conditioning system of the embodiment of the present invention energizes integrated control device composition block diagram.
Specific embodiment
Understand in order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing pair
The embodiment of the present invention is described in detail.It should be noted that in the absence of conflict, embodiment and reality in the application
The feature applied in example can mutual any combination.
Step shown in the flowchart of the accompanying drawings can be in a computer system such as a set of computer executable instructions
It executes.Also, although logical order is shown in flow charts, and it in some cases, can be to be different from herein suitable
Sequence executes shown or described step.
In order to reach purpose of the embodiment of the present invention, the embodiment of the invention provides a kind of energy supplies of electric refrigerating machine air-conditioning system
Integrated control method, as shown in Figure 1, the method may include S101-S103:
Refrigeration duty demand result in S101, the following preset duration for exporting preset load prediction neural network model
As emulation input condition, regularly send to preset Dynamic Simulation Model；Wherein, the load prediction neural network model
Input parameter includes the current operating data for energizing end.
In embodiments of the present invention, in order to overcome the above-mentioned deficiencies of the prior art, it provides a kind of empty for electric refrigerating machine
Adjusting system energizes integrated automation method for optimally controlling.This method is for solving present in current garden central cooling
The problem of energy supply distribution is uneven, refrigerant system efficiency is low, user side comfort not can guarantee.Emphasis solves current dynamic waterpower
Balance adjustment technology can not constrain phase with team control, chilled water supply water temperature dynamic regulation and the indoor relative humidity of refrigeration system
The problem of fusion.
In embodiments of the present invention, in order to predict the load condition of subsequent period in advance, can by load prediction technology,
The embodiment of the present invention uses the nerual network technique of artificial intelligence field, by load, the shadow in user's the past period
It rings factor data to be trained, obtains load prediction neural network model, and to the following preset duration (such as 24 hours) interior user
The load of side is predicted.
Optionally, the refrigeration duty demand in the following preset duration for exporting preset load prediction neural network model
As a result it as emulation input condition, regularly sends to before preset Dynamic Simulation Model, the method also includes:
Collect the operation data at the energy supply end；The operation data includes the current operating data and history run number
According to；
The load prediction neural network model is trained using the operation data as training set.
In embodiments of the present invention, above-mentioned load prediction neural network model can be as shown in Fig. 2, implement in the present invention
Before example scheme is implemented, the operation data at production capacity end can be collected in advance, which may include the current operating data
With history data (history data of a cold season as above).Optionally, the operation data may include but unlimited
In it is following any one or more: outdoor temperature Tout, outside relative humidity Hout, wind speed Fs, wind direction Fd, illuminance Lux, room
Interior temperature Tin, indoor relative humidity Hin and refrigeration duty Pcool；In this, as training set training load prediction neural network mould
Type.Trained load prediction neural network model can be obtained future by weather forecast data as input parameter
Refrigeration duty demand curve in a few hours.
It in embodiments of the present invention, is the precision for keeping load prediction neural network model, load prediction neural network mould
Rolling mode can be set into the training process of type, i.e., constantly adds new operation data, to reflect nearest bear in real time
Lotus situation.
It in embodiments of the present invention, can be by load prediction results (i.e. above-mentioned refrigeration duty demand result) with half an hour
(time step is adjustable) is to be sent to Dynamic Simulation Model in the period, the input condition as system emulation.
In embodiments of the present invention, the Dynamic Simulation Model can include but is not limited to it is following any one or more:
Electric refrigerating machine model, water pump model, cooling tower model and resistance of pipe system model.
In embodiments of the present invention, Dynamic Simulation Model is digital mechanism model (including the electric refrigerating machine mould of refrigeration system
Type, water pump model, cooling tower model, resistance of pipe system model etc.), the property of refrigeration system can be obtained by computer Simulation calculation
The state parameter (can include but is not limited to following optimized variables) of energy and each tie point.
Optionally, the input parameter of the load prediction neural network model further include: preset economic index；It is described
Preset economic index can include but is not limited to one or more of: cooling supply price, electricity rates and with water price lattice.
In embodiments of the present invention, the input parameter of simulation layer may include the refrigeration duty in the following preset duration above-mentioned
Demand as a result, or subsequent time prediction refrigeration duty；It can also include: outdoor temperature, outside relative humidity etc..
In embodiments of the present invention, the input parameter of Dynamic Simulation Model can also include in addition to load prediction results
Economic index, such as cooling supply price, electricity rates, with water price lattice.The global optimization of artificial intelligence field is combined on this basis
Algorithm (for example, can use evolution algorithm), turns to objective function with economic well-being of workers and staff maximum, carries out in different operation reserves
Optimizing, thus the optimum operation mode under finding corresponding load.
S102, emulation is optimized by the Dynamic Simulation Model, to optimize to preset optimized variable.
In embodiments of the present invention, Fig. 3 gives the Dynamic Simulation Model or dynamic optimization of the embodiment of the present invention
Model, the model can be made of simulation layer and optimization algorithm layer.Simulation layer is the digital physics of underlying physical equipment and pipe network
Model obtains the performance parameter of cold system and battalion under specified operating condition for carrying out simulation calculating to energy supply end cold system
Parameter is received, simulation layer constitutes the evaluation function of optimization algorithm layer.
In embodiments of the present invention, the optimized variable can include but is not limited to it is following any one or more: cold
Start number of units, cooling tower starting number of units, cooling water flow, chilled-water flow and chilled water supply water temperature.
In embodiments of the present invention, the method can also include: during optimizing to preset optimized variable, to abide by
Follow preset constraint condition；
The constraint condition can include but is not limited to it is following any one or more: cold maximum refrigerating capacity, cold
Minimum chilled-water flow, cold minimum cooling water flow, cold maximum chilled-water flow, cold maximum cooling water flow, freezing
Pump capacity range, cooling water pump range of flow and indoor maximum relative humidity.
In embodiments of the present invention, described by described dynamic when the optimized variable is the chilled water supply water temperature
State simulation model optimizes emulation, may include: to optimize to preset optimized variable
Using the indoor maximum relative humidity as the constraint condition, by preset in the Dynamic Simulation Model
Optimization algorithm, the highest chilled water supply water temperature currently allowed according to relative humidity calculation maximum in the user room fed back.
In embodiments of the present invention, in dynamic simulation optimization process, the adjustment of some optimized variables needs to follow specific
Constraint condition, wherein most important is exactly chilled water supply water temperature.When user side load is lower, freezing can be properly increased
Water supply water temperature is to reduce the power consumption of electric refrigerating machine.Its constraint condition followed is the indoor humidity feedback of user, the present invention
Embodiment can using the requirement in Ash Lay standard ASHRAE Standard 62-2001 standard to humidity as foundation, according to
The feedback of family side indoor relative humidity calculates the highest chilled water supply water temperature currently allowed, thus comfortable not sacrificing user
Energy Saving Control is carried out on the basis of property.
In embodiments of the present invention, dynamic simulation optimization process can be set to rolling optimization mode, such as be with half an hour
Step-length (time step is adjustable), the optimized operation scheme of optimizing subsequent time.
S103, the optimized variable after optimization is issued to the refrigeration system with energy end, and by described after optimization
Optimized variable controls the refrigeration system operation.
In embodiments of the present invention, optimization algorithm is empty in the design that optimized variable is constituted using simulation layer as evaluation function
It is interior to search for optimal operation reserve automatically, and finally obtained Optimum Design Results are issued to entity device layer, control system
The operation of cooling system, makes it close to best operating point.Optimization algorithm layer is come taking human as the time step rolling optimization of setting with this
It realizes tracking of the energy supply end to load, realizes dynamic optimization operational effect.
Optionally, the method can also include: according to the return water temperature and/or the temperature difference on waterpower loop, described in judgement
Whether the cooling capacity that chilled water is supplied in waterpower loop matches with energy end load demand；
Wherein, when the return water temperature and the temperature difference are equal to setting value, determine chilled water institute in the waterpower loop
The cooling capacity of supply is matched with described with energy end load demand；When the return water temperature and the temperature difference are not equal to setting value,
Determine the cooling capacity and the energy end load demand mismatch that chilled water is supplied in the waterpower loop.
In embodiments of the present invention, the dynamic hydraulic equilibrium regulation technology based on energy distribution can be imitative independently of dynamic
The a set of hydraulic equilibrium adjusting method really optimized.In waterpower loop, whether the cooling capacity that chilled water is supplied needs with end load
It asks and matches, be reflected directly on the return water temperature and the temperature difference of loop.When the return water temperature of loop or the temperature difference are equal to setting value,
Cooling capacity provided by then showing matches with end load demand, otherwise mismatches.Therefore, according to the return water temperature of loop or temperature
Difference, so that it may the which whether supply and demand of cooling capacity balances in accurate judgement loop, also may determine that the cooling capacity distribution between each loop is
No balance shows that the energy distribution between each loop also reaches when the return water temperature of all loops or the temperature difference reach unanimity
Balance.
In embodiments of the present invention, the dynamic hydraulic equilibrium control based on energy distribution equilibrium is with the return water of each loop
Temperature or the temperature difference calculate itself and setting according to the return water temperature or the temperature difference of each loop of actual measurement as controlled variable
Then the deviation and deviation variation rate of the temperature difference adjust respective loops water supply valve aperture by hydraulic equilibrium control algolithm, to phase
Cyclization road carries out dynamic regulation, realizes the equilibrium of supply and demand of each loop cooling capacity.
In embodiments of the present invention, Fig. 4 gives the information flow model in present invention implementation, can obtain day from weather station
Destiny evidence, and be associated with the refrigeration duty of energy scale acquisition, it is used for training load prediction neural network model.It is cold by end is energized
Freeze water supply water temperature, outdoor temperature, outside relative humidity, can scale acquisition refrigeration duty and with energy end indoor relative humidity into
Row association, establishes indoor relative humidity restricted model.Confession by each floor for return main's temperature acquisition and with the setting of energy supply end
Backwater temperature difference is compared, and adjusts each floor chilled water valve opening, constitutes inside building based on the dynamic that energy distribution is balanced
Hydraulic equilibrium regulating system.
In embodiments of the present invention, in conclusion the embodiment of the present invention use electric refrigerating machine system (including electricity system
Cold, cooling water pump, chilled water pump and cooling tower) Dynamic Simulation Model, the model support electric refrigerating machine, water pump, cooling tower
Mechanism model, it is maximum with electric refrigerating machine system benefit using load prediction and water, electricity, cold pricing information as input condition
Objective function is turned to, using the cold demand of user side and optimum humidity as constraint condition, most using global optimization approach Auto-matching
Good operation reserve, plus-minus load, the setting of water pump frequency and the start and stop of cooling tower fan and best return water including electric refrigerating machine
The calculating of temperature.The model rolls optimizing with time step set by user, so as to real-time response user side load variations,
Guarantee that electric refrigerating machine system is in optimized operation state in real time.
In embodiments of the present invention, the embodiment of the present invention will energize end and organically be coupled integrally, both with energy end
It ensure that and distribute balanced and comfort requirement with the dynamic power under the conditions of the different load of energy end, also ensure energy supply end most
Good economy operation.It is not in the unconspicuous phenomenon of individual loop refrigeration effects caused by cooling capacity distribution is uneven with energy end,
Efficient operating status can be then in any condition by energizing end, realize the reduction of building cooling supply energy consumption.The present invention
The progress of embodiment is the algorithm of support artificial intelligence field, dependence of the cooling supply adjusting to artificial experience is got rid of, by PLC
(programmable logic controller (PLC)) programming Control can fully achieve it is unmanned on duty, thus reduce energy supply end and with energy end fortune
Tie up cost.
The embodiment of the invention also provides a kind of electric refrigerating machine air-conditioning systems to energize integrated control device 1, such as Fig. 5
It is shown, including processor 11 and computer readable storage medium 12, it is stored with instruction in the computer readable storage medium 12,
When described instruction is executed by the processor 11, the energy supply of electric refrigerating machine air-conditioning system described in above-mentioned any one one is realized
The control method of body.
The embodiment of the present invention includes: it will be cold in the following preset duration of preset load prediction neural network model output
Workload demand result is regularly sent as emulation input condition to preset Dynamic Simulation Model；Wherein, the load prediction mind
Input parameter through network model includes the current operating data for energizing end；It is optimized by the Dynamic Simulation Model imitative
Very, to be optimized to preset optimized variable；The optimized variable after optimization is issued to the refrigeration system with energy end, and
The refrigeration system operation is controlled by the optimized variable after optimization.By the example scheme, end will be energized by realizing
With with can end organically couple integrally both ensure that with can the dynamic power under the conditions of end different load distribute equilibrium and easypro
Adaptive requirement, also ensures the Best Economy operation at energy supply end, to reduce energy supply end and the O&M cost with energy end.
It will appreciated by the skilled person that whole or certain steps, system, dress in method disclosed hereinabove
Functional module/unit in setting may be implemented as software, firmware, hardware and its combination appropriate.In hardware embodiment,
Division between the functional module/unit referred in the above description not necessarily corresponds to the division of physical assemblies；For example, one
Physical assemblies can have multiple functions or a function or step and can be executed by several physical assemblies cooperations.Certain groups
Part or all components may be implemented as by processor, such as the software that digital signal processor or microprocessor execute, or by
It is embodied as hardware, or is implemented as integrated circuit, such as specific integrated circuit.Such software can be distributed in computer-readable
On medium, computer-readable medium may include computer storage medium (or non-transitory medium) and communication media (or temporarily
Property medium).As known to a person of ordinary skill in the art, term computer storage medium is included in for storing information (such as
Computer readable instructions, data structure, program module or other data) any method or technique in the volatibility implemented and non-
Volatibility, removable and nonremovable medium.Computer storage medium include but is not limited to RAM, ROM, EEPROM, flash memory or its
His memory technology, CD-ROM, digital versatile disc (DVD) or other optical disc storages, magnetic holder, tape, disk storage or other
Magnetic memory apparatus or any other medium that can be used for storing desired information and can be accessed by a computer.This
Outside, known to a person of ordinary skill in the art to be, communication media generally comprises computer readable instructions, data structure, program mould
Other data in the modulated data signal of block or such as carrier wave or other transmission mechanisms etc, and may include any information
Delivery media.
Claims (10)
1. a kind of electric refrigerating machine air-conditioning system energizes integrated control method, which is characterized in that the described method includes:
Using the refrigeration duty demand result in the following preset duration of preset load prediction neural network model output as emulation
Input condition is regularly sent to preset Dynamic Simulation Model；Wherein, the input parameter of the load prediction neural network model
Current operating data including energizing end；
Emulation is optimized by the Dynamic Simulation Model, to optimize to preset optimized variable；
The optimized variable after optimization is issued to the refrigeration system with energy end, and passes through the optimized variable control after optimization
Make the refrigeration system operation.
2. electric refrigerating machine air-conditioning system according to claim 1 energizes integrated control method, which is characterized in that
It is inputted the refrigeration duty demand result in the following preset duration of preset load prediction neural network model output as emulation
Condition is regularly sent to before preset Dynamic Simulation Model, the method also includes:
Collect the operation data at the energy supply end；The operation data includes the current operating data and history data；
The load prediction neural network model is trained using the operation data as training set.
3. electric refrigerating machine air-conditioning system according to claim 2 energizes integrated control method, which is characterized in that institute
It states operation data to include any of the following or a variety of: outdoor temperature, outside relative humidity, wind speed, wind direction, illuminance and cold
Load.
4. electric refrigerating machine air-conditioning system according to claim 1 energizes integrated control method, which is characterized in that institute
State the input parameter of load prediction neural network model further include: preset economic index；
The preset economic index includes one or more of: cooling supply price, electricity rates and with water price lattice.
5. electric refrigerating machine air-conditioning system according to claim 1 energizes integrated control method, which is characterized in that institute
State optimized variable to include any of the following or a variety of: cold starts number of units, cooling tower starting number of units, cooling water flow, freezing
Water flow and chilled water supply water temperature.
6. electric refrigerating machine air-conditioning system according to claim 5 energizes integrated control method, which is characterized in that institute
State method further include: during optimizing to preset optimized variable, it then follows preset constraint condition；
The constraint condition includes any of the following or a variety of: cold maximum refrigerating capacity, cold minimum chilled-water flow, cold
Machine minimum cooling water flow, cold maximum chilled-water flow, cold maximum cooling water flow, chilled water pump range of flow, cooling
Pump capacity range and indoor maximum relative humidity.
7. electric refrigerating machine air-conditioning system according to claim 6 energizes integrated control method, which is characterized in that when
It is described that emulation is optimized by the Dynamic Simulation Model when optimized variable is the chilled water supply water temperature, with right
Preset optimized variable, which optimizes, includes:
Using the indoor maximum relative humidity as the constraint condition, pass through the preset optimization in the Dynamic Simulation Model
Algorithm, the highest chilled water supply water temperature currently allowed according to relative humidity calculation maximum in the user room fed back.
8. electric refrigerating machine air-conditioning system described in -7 any one energizes integrated control method according to claim 1,
It is characterized in that, the Dynamic Simulation Model includes any of the following or a variety of: electric refrigerating machine model, water pump model, cooling tower
Model and resistance of pipe system model.
9. electric refrigerating machine air-conditioning system according to claim 1 energizes integrated control method, which is characterized in that institute
State method further include: according to the return water temperature and/or the temperature difference on waterpower loop, judge that chilled water is supplied in the waterpower loop
Cooling capacity whether with can end load demand match；
Wherein, when the return water temperature and the temperature difference are equal to setting value, determine that chilled water is supplied in the waterpower loop
Cooling capacity with it is described with can end load demand match；When the return water temperature and the temperature difference are not equal to setting value, determine
The cooling capacity and the energy end load demand mismatch that chilled water is supplied in the waterpower loop.
10. a kind of electric refrigerating machine air-conditioning system energizes integrated control device, including processor and computer-readable storage
Medium is stored with instruction in the computer readable storage medium, which is characterized in that when described instruction is executed by the processor
When, realize that electric refrigerating machine air-conditioning system as described in any one of claims 1-9 energizes integrated control method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811091228.0A CN109341010B (en) | 2018-09-19 | 2018-09-19 | Energy supply integrated control method and device for air conditioning system of electric refrigerator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811091228.0A CN109341010B (en) | 2018-09-19 | 2018-09-19 | Energy supply integrated control method and device for air conditioning system of electric refrigerator |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109341010A true CN109341010A (en) | 2019-02-15 |
| CN109341010B CN109341010B (en) | 2021-04-30 |
Family
ID=65305697
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811091228.0A Active CN109341010B (en) | 2018-09-19 | 2018-09-19 | Energy supply integrated control method and device for air conditioning system of electric refrigerator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109341010B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110186156A (en) * | 2019-06-03 | 2019-08-30 | 西安锦威电子科技有限公司 | Refrigeration plant Fuzzy control system |
| CN111765604A (en) * | 2019-04-01 | 2020-10-13 | 珠海格力电器股份有限公司 | Control method and device of air conditioner |
| CN113776171A (en) * | 2020-06-10 | 2021-12-10 | 中兴通讯股份有限公司 | Refrigeration equipment control method and device, computer equipment and computer readable medium |
| CN114688692A (en) * | 2020-12-30 | 2022-07-01 | 北京天诚同创电气有限公司 | Load prediction method, system and device |
| WO2023010556A1 (en) * | 2021-08-06 | 2023-02-09 | 西门子瑞士有限公司 | Dynamic prediction control method, apparatus and system for precision air conditioner |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004280450A (en) * | 2003-03-14 | 2004-10-07 | Toshiba Corp | Device for automatic modeling of plant model |
| CN101667013A (en) * | 2009-09-04 | 2010-03-10 | 天津大学 | Control method of optimized running of combined cooling and power distributed energy supply system of micro gas turbine |
| US20100218108A1 (en) * | 2009-02-26 | 2010-08-26 | Jason Crabtree | System and method for trading complex energy securities |
| CN102779228A (en) * | 2012-06-07 | 2012-11-14 | 华南理工大学 | Method and system for online prediction on cooling load of central air conditioner in marketplace buildings |
| CN104633829A (en) * | 2013-11-06 | 2015-05-20 | 上海思控电气设备有限公司 | Building cooling station energy-saving control device and method thereof |
-
2018
- 2018-09-19 CN CN201811091228.0A patent/CN109341010B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004280450A (en) * | 2003-03-14 | 2004-10-07 | Toshiba Corp | Device for automatic modeling of plant model |
| US20100218108A1 (en) * | 2009-02-26 | 2010-08-26 | Jason Crabtree | System and method for trading complex energy securities |
| CN101667013A (en) * | 2009-09-04 | 2010-03-10 | 天津大学 | Control method of optimized running of combined cooling and power distributed energy supply system of micro gas turbine |
| CN102779228A (en) * | 2012-06-07 | 2012-11-14 | 华南理工大学 | Method and system for online prediction on cooling load of central air conditioner in marketplace buildings |
| CN104633829A (en) * | 2013-11-06 | 2015-05-20 | 上海思控电气设备有限公司 | Building cooling station energy-saving control device and method thereof |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111765604A (en) * | 2019-04-01 | 2020-10-13 | 珠海格力电器股份有限公司 | Control method and device of air conditioner |
| CN111765604B (en) * | 2019-04-01 | 2021-10-08 | 珠海格力电器股份有限公司 | Control method and device of air conditioner |
| CN110186156A (en) * | 2019-06-03 | 2019-08-30 | 西安锦威电子科技有限公司 | Refrigeration plant Fuzzy control system |
| CN113776171A (en) * | 2020-06-10 | 2021-12-10 | 中兴通讯股份有限公司 | Refrigeration equipment control method and device, computer equipment and computer readable medium |
| CN113776171B (en) * | 2020-06-10 | 2024-02-13 | 中兴通讯股份有限公司 | Refrigeration equipment control method, refrigeration equipment control device, computer equipment and computer readable medium |
| CN114688692A (en) * | 2020-12-30 | 2022-07-01 | 北京天诚同创电气有限公司 | Load prediction method, system and device |
| CN114688692B (en) * | 2020-12-30 | 2023-10-20 | 北京天诚同创电气有限公司 | Load prediction method, system and device |
| WO2023010556A1 (en) * | 2021-08-06 | 2023-02-09 | 西门子瑞士有限公司 | Dynamic prediction control method, apparatus and system for precision air conditioner |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109341010B (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109341010A (en) | A kind of electric refrigerating machine air-conditioning system energizes integrated control method and device | |
| CN105320118B (en) | Air-conditioning system electricity needs response control mehtod based on cloud platform | |
| CN108039710B (en) | Step characteristic-based air conditioner load-participating power grid day-ahead scheduling method | |
| CN107726546B (en) | The central air-conditioning intelligence system and its control method of unmanned operation | |
| US10527304B2 (en) | Demand response based air conditioning management systems and method | |
| CN113091123A (en) | Building unit heat supply system regulation and control method based on digital twin model | |
| CN108361885B (en) | Dynamic planning method for ice storage air conditioning system | |
| CN107781947A (en) | A kind of air conditioning system Cooling and Heat Source forecast Control Algorithm and device | |
| CN105674487B (en) | Dynamic hydraulic balance adjusting method for central air conditioning system | |
| CN101949559A (en) | Intelligent energy-saving mixed water heat supply method | |
| CN105719047A (en) | Allocation of energy production changes to meet demand changes | |
| CN112611076B (en) | Subway station ventilation air conditioner energy-saving control system and method based on ISCS | |
| CN107421029A (en) | A kind of end cold balance control method | |
| CN109612047A (en) | The supply air temperature control method of air conditioning system with variable | |
| CN113110057A (en) | Heating power station energy-saving control method based on artificial intelligence and intelligent decision system | |
| CN110195927A (en) | A kind of the chilled water system control method and device of distributed centralization air-conditioning | |
| CN111025895A (en) | Building energy-saving control system based on artificial intelligence | |
| CN113110056B (en) | Heat supply intelligent decision-making method and intelligent decision-making machine based on artificial intelligence | |
| Li et al. | Reinforcement learning-based demand response strategy for thermal energy storage air-conditioning system considering room temperature and humidity setpoints | |
| CN114282708B (en) | Cross-region comprehensive energy system optimization operation method and system considering multi-scale demand response | |
| CN105240993A (en) | Fine energy-saving control system of central air conditioner and achieving method of fine energy-saving control system | |
| CN115614812A (en) | Hydraulic balance management method based on Internet of things and edge computing technology | |
| CN109190988A (en) | A kind of Demand Side Response game method for realizing the optimal collaboration of temperature control load | |
| CN118153353A (en) | Dynamic simulation optimizing method and related device for air conditioner | |
| CN115585501B (en) | Central heating user side autonomous regulating system and method based on network intelligent control |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |