CN110288164B - Predictive control method for building air-conditioning refrigeration station system - Google Patents
Predictive control method for building air-conditioning refrigeration station system Download PDFInfo
- Publication number
- CN110288164B CN110288164B CN201910589020.XA CN201910589020A CN110288164B CN 110288164 B CN110288164 B CN 110288164B CN 201910589020 A CN201910589020 A CN 201910589020A CN 110288164 B CN110288164 B CN 110288164B
- Authority
- CN
- China
- Prior art keywords
- temperature
- cooling water
- water
- water pump
- outdoor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004378 air conditioning Methods 0.000 title claims abstract description 93
- 238000005057 refrigeration Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 32
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 160
- 239000000498 cooling water Substances 0.000 claims abstract description 82
- 238000005457 optimization Methods 0.000 claims abstract description 44
- 238000013528 artificial neural network Methods 0.000 claims abstract description 38
- 238000005265 energy consumption Methods 0.000 claims abstract description 30
- 238000005096 rolling process Methods 0.000 claims abstract description 12
- 238000012706 support-vector machine Methods 0.000 claims abstract description 7
- 238000001816 cooling Methods 0.000 claims description 20
- 238000001914 filtration Methods 0.000 claims description 17
- 238000005070 sampling Methods 0.000 claims description 15
- 238000007710 freezing Methods 0.000 claims description 12
- 230000008014 freezing Effects 0.000 claims description 12
- 239000008400 supply water Substances 0.000 claims description 12
- 238000011217 control strategy Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 238000004134 energy conservation Methods 0.000 claims description 6
- 230000005855 radiation Effects 0.000 claims description 6
- 239000002131 composite material Substances 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims description 2
- 239000013598 vector Substances 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract 1
- 230000008878 coupling Effects 0.000 description 6
- 238000010168 coupling process Methods 0.000 description 6
- 238000005859 coupling reaction Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000010438 heat treatment Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000004886 process control Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004800 variational method Methods 0.000 description 2
- 238000009423 ventilation Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Biomedical Technology (AREA)
- Mechanical Engineering (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Fuzzy Systems (AREA)
- Molecular Biology (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
Abstract
The invention discloses a prediction control method for a building air-conditioning refrigeration station system, which constructs a building air-conditioning system load prediction model, an air-conditioning refrigeration station system prediction model, a refrigeration station prediction control optimization objective function and a prediction control system optimization algorithm, adopts a neural network or a support vector machine to construct the building air-conditioning system load prediction model and the building air-conditioning refrigeration station system prediction model, and takes an optimized performance index as the sum of squares of deviations between an actual value and an expected value of an energy efficiency index EERr of a refrigeration station. Based on a predictive control rolling optimization algorithm, optimal set values of controlled parameters of the four field controllers of chilled water supply temperature, chilled water pump frequency or chilled water flow, cooling water return temperature, cooling water pump frequency or cooling water flow are subjected to optimization calculation, and the field controllers automatically enable controlled variables to follow the optimal set values through closed-loop control, so that the system can reduce energy consumption of a refrigerating station on the premise of building cold quantity demand.
Description
Technical Field
The invention belongs to the technical field of control of building air-conditioning refrigeration stations, and particularly relates to a predictive control method of a building air-conditioning refrigeration station system.
Background
Along with the gradual acceleration of the urbanization development pace of China, the urban building industry is rapidly developed, and the energy consumption of buildings tends to rise continuously. In China, the building energy consumption accounts for about 30% of the total energy consumption of the social terminal. The heating, ventilating, air conditioning and refrigerating station system is one of indispensable components of a building, the energy consumption of the heating, ventilating, air conditioning and refrigerating station system accounts for about 60% of the total energy consumption of the building, and the high energy consumption of the air conditioning and refrigerating station system becomes the largest brake which restricts the development of the building to green energy conservation. From a large amount of domestic project data, the EER of the central air conditioner is usually below 2.0, the average value of the central air conditioner industry is about 1.8-2.0, and the energy efficiency is low. The optimization transformation and the energy-saving control strategy research based on the building air-conditioning refrigeration station system are generally concerned by governments and the persons in the industry. However, the improvement of the internal structure design of the air conditioning system can lead to the increase of the basic investment, and compared with the economic benefit, the energy-saving benefit is not obvious; only by adopting an optimization control strategy based on load prediction, the cooling requirement of a building space can be met, the energy consumption of the building air-conditioning refrigeration station system is reduced to the maximum extent, and the energy conservation of the air-conditioning refrigeration station system is realized in the true sense. The building air-conditioning refrigeration station system has the characteristics of multivariable, strong coupling, large time lag and large inertia, and an accurate mathematical model is difficult to establish. The traditional PID control is difficult to adapt to and process the complex coupling relation among the variables of the system. The prediction control algorithm is suitable for the control of the building air-conditioning refrigeration station system by combining the load prediction with the characteristics that the prediction control algorithm has low requirements on models and can process the problems of constraint, coupling and hysteresis. The prediction control is actually the optimal control of the system running state, the energy consumption and the requirement of meeting the load can be integrated to be used as the optimal performance index to obtain the optimal solution of the controlled variable, so that the purposes of meeting the cold quantity requirement and saving energy are achieved, the state variable and the optimal target value of the system at the next moment can be predicted in advance, the running equipment responds in advance, and the dynamic performance deterioration of the system caused by the system lag is reduced; meanwhile, the problems of interference and model uncertainty in the system operation process can be solved through rolling optimization.
In summary, the existing building air-conditioning refrigeration station system has the problems of high energy consumption, poor control performance, serious loop coupling and poor energy-saving effect, and the problems affect the development of green energy conservation of buildings.
Therefore, how to solve the above problems becomes a focus of research by those skilled in the art.
Disclosure of Invention
The invention aims to provide a predictive control method for a building air-conditioning refrigeration station system, which can completely solve the defects of the prior art.
The purpose of the invention is realized by the following technical scheme:
a predictive control method for a building air conditioning refrigeration station system comprises the following steps:
1) An optimization layer of the control system optimizes the set value of the controlled parameter of the controller of the field control layer by utilizing a neural network predictive control strategy, and the optimization target is to enable the energy efficiency index EEr of the chilled water system to reach the set value meeting the requirements of cold quantity and energy conservation;
2) Collecting operation data of an air-conditioning refrigeration station system, preprocessing the data, and adopting a composite filtering algorithm, wherein the composite filtering algorithm comprises the following steps: filtering by using a sliding weighted arithmetic mean filtering algorithm and a sliding median mean filtering algorithm;
3) Establishing a load prediction model of the air conditioning system by using a neural network or a support vector machine;
4) Establishing a prediction model of a building air-conditioning refrigeration station system by utilizing a neural network or a support vector machine;
5) Determining the performance index of the predictive control optimization of the air conditioning system, namely an objective function:
wherein J (EERr) [ k ]]The optimized performance index of the air-conditioning refrigeration station system is represented; m represents the predicted step number; t is t 1 Representing an initial instant of the prediction time domain; EERr [ k ]]The energy efficiency ratio of the air-conditioning refrigeration system at the k-th moment is represented; EERr set [k]Representing the set value of the energy efficiency ratio of the air-conditioning refrigeration system at the kth moment;
6) Determining that the neural network prediction controller structure of the building air-conditioning refrigeration station system is a three-layer neural network structure, and the method comprises the following steps:
1) For a system with a single refrigerating machine, a chilled water pump and a cooling water pump running, a control variable chilled water supply water temperature Tchws, a chilled water pump frequency fpum or chilled water flow, a cooling water return water temperature Tcws, a cooling water pump frequency fp or cooling water flow influencing performance indexes are output as a controller and are transmitted to a field controller to be used as a set value of a controlled parameter, and an outdoor temperature Tout, an outdoor relative humidity Rpout, a system cold load Q at the current moment, an EERr set value EERrset and a threshold value-1 are input as the controller;
2) For a system with a plurality of refrigerators, chilled water pumps and cooling water pumps running, the supply water temperature Tchws of a control variable chilled water main supply pipe, the frequency fpumn or the flow rate of chilled water of each chilled water pump, the return water temperature Tcws of a cooling water main return pipe, the frequency fpn of each cooling water pump or the flow rate of cooling water, which influence performance indexes, are output as controllers and are transmitted to a field controller to be used as set values of controlled parameters, wherein subscripts in fpumn and fpn represent the nth chilled water pump or the cooling water pump; taking the outdoor temperature Tout, the outdoor relative humidity Rpout, the system cold load Q at the current moment, the EERr at the current moment, the EERset value EERset and the threshold value-1 as the input of a controller;
7) Carrying out online optimization training on the neural network prediction controller of the building air-conditioning refrigeration station system, carrying out rolling optimization on prediction control according to the following formula to obtain a neural network controller weight value which enables an optimization objective function to be optimal, and further obtain an optimal control quantity:
W＝W+ΔW，
wherein k is any time, x [ k ] is related state variable parameters of the building air-conditioning refrigeration station system at the time k, namely the outdoor temperature, the outdoor relative humidity, the return air temperature, the system cold load and the current EERr, at the current time, wherein the outdoor temperature, the outdoor relative humidity and the return air temperature are measured values, and the system cold load and the current EERr are calculated values according to the electricity consumption and the refrigeration capacity provided by the refrigeration station; x (k + 1) is a set value of EERr at the next time; u [ k ] is the optimal control quantity at k time after the optimization of the neural network prediction controller is finished, namely the set value of the controlled parameter of the controller of the field control layer; u' [ k + i-1] is a control quantity calculated according to the weight of the predictive controller at the last moment in the rolling optimization process; f (-) represents a prediction model of a controlled object, namely a built refrigeration station system neural network prediction model; g (-) represents a neural network controller model; l [ k ] represents the optimized performance index at each moment, namely the deviation square sum between the actual value and the expected value of EERr; λ [ k ] and γ [ k ] represent lagrange multiplier vectors;
8) And repeating the operation in each sampling period, and respectively calculating the control quantity value at each later moment until the control process is finished.
Preferably, the EERr is calculated by the following formula:
EERr＝Q ch /P total
wherein P is total The total energy consumption of each equipment of the air-conditioning refrigeration station system is expressed in kW, and can be obtained according to the following formula:
P total ＝P chiller +P pumpch +P pumpc +P tower
wherein P is chiller For water chiller energy consumption, P pumpch For energy consumption of chilled water pumps, P pumpc For cooling water pump energy consumption, P tower Energy consumption for cooling towers;
the energy consumption of the water chilling unit is as follows:
P chiller ＝Q ch /COP
the COP represents the operation energy efficiency of the water chilling unit, and is dimensionless, and the Qch is the system cooling load.
Preferably, the sliding median average filtering algorithm includes:
1) Aiming at any J-th original sampling data, the front N-1 original sampling data and the rear N original sampling data form a group of 2N data;
2) Sorting the 2N data;
3) Removing a maximum value and a minimum value before and after the sorted data;
4) Calculating the average value of the residual data, and storing the average value as the J-th sampling data;
5) Then, the J +1 th data is processed in the same way until all the data are processed;
where J and N represent selectable variables that can be modified depending on the actual filtering effect.
Preferably, the air conditioning system load prediction model includes:
1) Air conditioning system load prediction model structure
The input parameter of the prediction model has an outdoor temperature T out Outdoor relative humidity RH out Solar radiation intensity I and outdoor wind speed S north Outdoor wind speed S east The load factor L of the refrigerator, the system cooling load Qch at the current moment, and the system cooling load Qch at the same moment before the day- day The cooling load Qch of the system at the same time before the week week The output of the load prediction model is the cold load Q [ k + 1] of the system at the next moment]. In the above symbols, k represents the current time, and k +1 represents the next time of the current time;
2) Sample data
The sample data is refrigerating station system operation data and outdoor meteorological parameter data in refrigerating season, including outdoor temperature T out Outdoor relative humidity RH out Solar radiation intensity I and outdoor wind speed S north Outdoor wind speed S east The load rate L of the cold machine and the flow rate and the temperature difference of the chilled water supply and return water of the refrigeration station are calculated to obtain a load value, and the load is calculated according to the following formula:
Q ch ＝c·m chw ·(T chwr -T chws )
in the formula, Q ch The system cold load at the current moment, namely the cold quantity prepared by the water chilling unit is expressed in kW unit; c represents the specific heat capacity of water, and the unit kJ/(kg. K); m is chw The mass flow of the freezing water is expressed in unit kg/s; t is chws Represents the temperature of chilled water supply in units; t is chwr The acquired data cover the whole dynamic range of the system according to the unit ℃ and the return water temperature of the chilled water.
Preferably, the building air conditioning refrigeration station system prediction model comprises:
1) Determining air-conditioning refrigeration station system prediction model structure
1) For a system with a single refrigerator, chilled water pump, and cooling water pump operating, the prediction model input parameter has chilled water supply temperature T chws Frequency f of the chilled water pump pum Or the flow rate of the freezing water and the return water temperature T of the cooling water cws Frequency f of cooling water pump p Or cooling water flow, outdoor temperature T out Outdoor relative humidity RH out The system cold load Qch at the current moment, the energy efficiency index EERr of the chilled water system at the current moment, and the output of the system load prediction model of the air-conditioning refrigeration station is the next-moment EERr [ k + 1]]. In the above symbols, k represents the current time, and k +1 represents the next time of the current time;
2) For a system with multiple refrigerators, chilled water pumps, and cooling water pumps operating, the input parameter to the predictive model is the chilled water mains supply water temperature T chws Frequency f of each chilled water pump pumn Or the flow rate of the freezing water and the return water temperature T of the cooling water main return pipe cws Frequency f of each cooling water pump pn Or cooling water flow, outdoor temperature T out Outdoor relative humidity RH out The system cold load Q at the current moment, the energy efficiency index EERr of the chilled water system at the current moment, and the output of the system load prediction model of the air-conditioning refrigeration station is the EERr [ k + 1] at the next moment]. Wherein f is pumn And f pn The subscript n in the (1) indicates the nth refrigerating water pump or cooling water pump;
2) Sample data
1) For a system with a single refrigerating machine, a refrigerating water pump and a cooling water pump operating, the sample data is refrigerating station system operating data and outdoor meteorological parameter data in the refrigerating season, including the supply water temperature T of the refrigerating water chws Frequency f of the chilled water pump pum Or the flow rate of the freezing water and the return water temperature T of the cooling water main return pipe cws Frequency f of cooling water pump p Or cooling water flow, outdoor temperature T out Outdoor relative humidity RH out Return air temperature T in And the flow rate and the temperature difference of the refrigerating water of the refrigerating station, and calculating the load value according to the flow rate and the temperature difference;
2) For multiple refrigerators, chilled water pumps, and cooling water pump operationThe sample data is the operation data of the refrigerating station system in the refrigerating season and the outdoor meteorological parameter data, and comprises the water supply temperature T of the main chilled water supply pipe chws Frequency f of each refrigerating water pump pumn Or the flow rate of the freezing water and the return water temperature T of the cooling water main return pipe cws Frequency f of cooling water pump pn Or cooling water flow, outdoor temperature T out Outdoor relative humidity RH out Return air temperature T in And the flow and the temperature difference of the refrigeration station refrigerated water main pipe, and the load value is calculated according to the flow and the temperature difference, and the acquired data cover the whole dynamic range of the system.
Compared with the prior art, the invention has the beneficial effects that:
the prediction control algorithm of the invention has low requirements on models and can deal with the problems of constraint, coupling and hysteresis, and is suitable for process control of the building air-conditioning refrigeration station system. In recent years, with the development and application of predictive control strategies, the excellent controllability of the predictive control strategies is more and more favored by heating and ventilation workers. The strategy can use a prediction model to predict the error between the future output of the system and the set value, and can use a rolling optimization strategy to obtain the current optimal control input sequence. The invention provides an intelligent control method aiming at the control difficulty of a multi-input multi-output nonlinear time-varying system with large hysteresis characteristic in the existing building air-conditioning refrigeration station and integrating the advantages of a neural network, optimal control and predictive control. The method is based on a variational method, utilizes a prediction rolling optimization idea to train a multilayer feedforward neural network, then uses the multilayer feedforward neural network as an optimization feedback controller to solve an optimization feedback solution of a time-varying multi-input multi-output nonlinear system, and can solve the optimization control problem of the nonlinear system under the condition of moderate calculated amount and occupied storage area capacity. Aiming at a building chilled water cooling type air conditioning system, the invention firstly carries out building air conditioning load prediction, constructs a refrigerating station system prediction model, and determines a prediction control optimization performance index as the sum of squares of deviations between an actual value and an expected value of an Energy Efficiency index EER (Energy Efficiency Ratio) of the refrigerating station system.
Drawings
FIG. 1 is a block diagram of the predictive control system of the invention;
FIG. 2 is a diagram of a neural network model for load prediction of a building air conditioning system;
FIG. 3 is a diagram of a neural network prediction model of a system for operation of a single refrigerator, a chilled water pump and a cooling water pump of a building air conditioning refrigeration station;
FIG. 4 is the system neural network predictive controller structure for the operation of single refrigerator, freezing water pump and cooling water pump in the air-conditioning refrigeration station of the building.
Detailed Description
The invention will be further described with reference to specific embodiments and the accompanying drawings.
Example one
As shown in fig. 1 to 4, a predictive control method for a building air conditioning refrigeration station system includes the following steps:
the first step is as follows: determining predictive control system architecture
The control system is of a two-layer structure, the upper layer is an optimization layer, and the lower layer is a field control layer. The optimization layer utilizes a neural network predictive control strategy to optimize the set value of the controlled parameter of the controller of the field control layer, and the optimization target is to enable the EERr value of the energy efficiency index (the refrigerating capacity generated by each unit energy consumption of the refrigerating station) of the chilled water system to reach the set value, thereby achieving the purpose of meeting the requirements of refrigerating capacity and energy conservation.
EERr is calculated according to the following formula
EERr＝Q ch /P total
In the formula, P total The total energy consumption in kW of each unit of the air-conditioning refrigeration station system can be obtained by the following formula
P total ＝P chiller +P pumpch +P pumpc +P tower
Wherein P is chiller For water chiller energy consumption, P pumpch For energy consumption of chilled water pumps, P pumpc For cooling water pump energy consumption, P tower Energy consumption for cooling tower.
Energy consumption of the water chilling unit:
P chiller ＝Q ch /COP
in the formula, COP represents the operation energy efficiency of the water chilling unit and is dimensionless.
The controller of the field control layer controls the refrigerator, the cooling tower, the chilled water pump and the cooling water pump by adopting a PID control method based on the optimized set value of the controlled parameters.
The second step is that: collecting operation data of air-conditioning refrigeration station system and preprocessing the data
The filtering is carried out by adopting a sliding median average filtering algorithm, random errors and peak errors in actual data can be effectively removed by the algorithm, and the actual data of the air-conditioning system can be restored as far as possible. The filtering algorithm is as follows:
1) Aiming at the J-th original sampling data, forming a group of 2N data with the front N-1 original sampling data and the back N original sampling data;
2) Sorting the 2N data;
3) Removing a maximum value and a minimum value before and after the sorted data;
4) Calculating the average value of the residual data, and storing the average value as the J-th sampling data;
5) Then, the J +1 th data is processed in the same way until all data is processed.
The third step: method for establishing air conditioning system load prediction model by using neural network or support vector machine
1) Air conditioning system load prediction model structure
The input parameter of the prediction model has an outdoor temperature T out (k) Outdoor relative humidity RH out (k) Solar radiation intensity I (k), outdoor wind speed S north (k) Outdoor wind speed (east direction) S east (k) The cold load rate L (k), the system cooling load Qch (k) at the current moment, and the system cooling load Qch at the same moment before one day- day (k) System cooling load Qch- week (k) The output of the load prediction model is the system cooling load Q (k + 1) at the next moment. In the above notation, k represents the current time, and k +1 represents the time next to the current time. Building air conditioning systemThe structure of the neural network model for system load prediction is shown in figure 1.
2) Sample data
The sample data is refrigerating station system operation data and outdoor meteorological parameter data in refrigerating season, including outdoor temperature T out (k) Outdoor relative humidity RH out (k) Solar radiation intensity I (k), outdoor wind speed S north (k) Outdoor wind speed (east direction) S east (k) The load rate L (k) of the cold machine, the flow rate and the temperature difference of the chilled water supply and return water of the refrigeration station are calculated to obtain a load value, and the load is calculated according to the following formula to obtain the load value
Q ch ＝c·m chw ·(T chwr -T chws )
In the formula, Q ch The unit kW represents the cooling capacity prepared by the water chilling unit; c represents the specific heat capacity of water, and the unit kJ/(kg. K); m is chw (also can be written as m) e ) The mass flow of the freezing water is expressed in unit kg/s; t is a unit of chws (also writable as T eo ) The temperature of the chilled water supply water is expressed in unit; t is chwr (also writable as T) ei ) The return water temperature of the chilled water is expressed in unit ℃.
The collected data covers the entire dynamic range of the system.
The fourth step: building air-conditioning refrigeration station system prediction model established by using neural network or support vector machine
1) System prediction model structure for determining air-conditioning refrigeration station
(1) For a system with a single refrigerating machine, a refrigerating water pump and a cooling water pump running, the input parameter of the prediction model is the supply water temperature T of the refrigerating water chws (k) Frequency f of the chilled water pump pum (k) Cooling water return temperature T cws (k) Frequency f of cooling water pump p (k) Outdoor temperature T out (k) Outdoor relative humidity RH out (k) The system load prediction model comprises a current-time system cold load Q (k), an energy efficiency index EERr (k) of a chilled water system at the current time, and the output of the air-conditioning refrigeration station system load prediction model is the next-time EERr (k + 1). In the above notation, k represents the current time, and k +1 represents the time next to the current time.
(2) For multiple refrigerators and chilled waterThe system for running pump and cooling water pump, the input parameter of prediction model has the water supply temperature T of main water supply pipe of chilled water chws (k) Frequency f of each refrigerating water pump pumn (k) The return water temperature T of the cooling water main return pipe cws (k) Frequency f of each cooling water pump pn (k) Outdoor temperature T out (k) Outdoor relative humidity RH out (k) The system load prediction model comprises a current-time system cold load Q (k), an energy efficiency index EER (refrigerating capacity generated by each unit of energy consumption of a refrigerating station) EERr (k) of a chilled water system at the current time, and the output of the system load prediction model of the air-conditioning refrigerating station is the next-time EERr (k + 1). Wherein f is pumn (k) And f pn (k) The subscript n in (1) denotes an nth chilled water pump or cooling water pump.
For a system with a single refrigerator, a refrigerating water pump and a cooling water pump running, the structure of the neural network prediction model of the building air-conditioning refrigerating station system is shown in fig. 2.
2) Sample data
(1) For a system with a single refrigerating machine, a refrigerating water pump and a cooling water pump running, the sample data is the running data of the refrigerating station system in the refrigerating season and the outdoor meteorological parameter data, including the supply water temperature T of the refrigerating water chws (k) Frequency f of the chilled water pump pum (k) The return water temperature T of the cooling water main return pipe cws (k) Frequency f of cooling water pump p (k) Outdoor temperature T out (k) Outdoor relative humidity RH out (k) Return air temperature T in (k) And the flow rate and the temperature difference of the chilled water supply and return water of the refrigeration station are calculated to obtain a load value.
(2) For a system with a plurality of refrigerators, chilled water pumps and cooling water pumps running, the sample data is the running data of the refrigeration station system in the refrigeration season and the outdoor meteorological parameter data, including the water supply temperature T of the chilled water main water supply pipe chws (k) Frequency f of each refrigerating water pump pumn (k) The return water temperature T of the cooling water main return pipe cws (k) Frequency f of cooling water pump pn (k) Outdoor temperature T out (k) Outdoor relative humidity RH out (k) Return air temperature T in (k) And the flow rate and the temperature difference of the chilled water supply and return water of the refrigeration station are calculated to obtain a load value.
The collected data covers the entire dynamic range of the system.
The fifth step: predictive control of building air conditioning systems
1) Determining a predictive control objective function for an air conditioning system
The predictive control optimization objective function of the building air conditioning system is as follows:
wherein J (EERr) [ k ]]The method comprises the steps of representing an optimized performance index of an air-conditioning refrigeration station system; m represents the predicted step number; t is t 1 Representing an initial instant of the prediction time domain; EERr [ k ]]The energy efficiency ratio of the air-conditioning refrigeration system at the k-th moment is represented; EERr set [k]And the energy efficiency ratio set value of the air-conditioning refrigeration system at the k-th moment is shown.
2) Neural network prediction controller structure for determining building air-conditioning refrigeration station system
The prediction controller selects a three-layer neural network.
(1) For a system with a single refrigerating machine, a chilled water pump and a cooling water pump running, the control variables of chilled water supply water temperature Tchws (k), chilled water pump frequency fpum (k), cooling water return water temperature Tcws (k) and cooling water pump frequency fp (k) influencing performance indexes are output as controllers and transmitted to a field controller to be used as set values of controlled parameters, and outdoor temperature Tout (k), outdoor relative humidity RHOut (k), current time system cold load Q (k), current time EERr (k), EERr set values EERset and threshold-1 are input as controllers.
(2) In a system for operating a plurality of refrigerators, chilled water pumps and cooling water pumps, the water supply temperature Tchws (k) of a chilled water main water supply pipe, the frequency fpumn (k) of the chilled water pumps, the return water temperature Tcws (k) of a cooling water main water return pipe and the frequency fpn (k) of the cooling water pumps, which influence performance indexes, are output as controllers and are transmitted to a field controller to be used as set values of controlled parameters, and the outdoor temperature Tout (k), the outdoor relative humidity Rpout (k), the system cold load Q (k) at the current moment, the EERr (k) at the current moment, the set value EERrset of the EERrset and a threshold value-1 are input as the controllers.
Fig. 3 is a neural network predictive controller architecture for a building air conditioning refrigeration station system for a system operating with a single chiller, chilled water pump and cooling water pump.
3) On-line optimization training for neural network prediction controller of building air-conditioning refrigeration station system
The predictive control system block diagram is shown in FIG. 4, where x [ k ]]Relevant state variable parameters of the building air-conditioning refrigeration station system at the moment k, namely the outdoor temperature, the outdoor relative humidity, the return air temperature, the system cold load and the current EERr, wherein the outdoor temperature, the outdoor relative humidity and the return air temperature are measured values, and the system cold load and the current EERr are calculated values according to the power consumption and the refrigeration quantity provided by the refrigeration station;
predicting model output at the k +1 moment, namely an EERr value at the next moment; x [ k + 1]]Is the set value of EERr at the next time; u [ k ]]The optimal control quantity at the time k after the optimization of the neural network prediction controller is finished, namely the set value of the controlled parameter of the controller of the field control layer; u' [ k + i-1]]And the control quantity is calculated according to the weight of the predictive controller at the previous moment in the rolling optimization process, and the control quantity is not optimized according to the variable value of the system running state at the current moment.
The predictive control performs a rolling optimization according to the following formula to obtain a control quantity that optimizes the optimization objective function:
W＝W+ΔW
and repeating the operation in each sampling period, and respectively calculating the control quantity value at each later moment until the control process is finished.
In the embodiment, the predictive control algorithm has the advantages of low requirements on models and capability of processing the problems of constraint, coupling and hysteresis, and is suitable for process control of the building air-conditioning refrigeration station system. In recent years, with the development and application of predictive control strategies, the excellent controllability of the predictive control strategies is more and more favored by heating and ventilation workers. The strategy can use a prediction model to predict the error between the future output of the system and the set value, and can adopt a rolling optimization strategy to obtain the current optimal control input sequence. The invention provides an intelligent control method aiming at the control difficulty of a multi-input multi-output nonlinear time-varying system with large hysteresis characteristic in the existing building air-conditioning refrigeration station and integrating the advantages of a neural network, optimal control and predictive control. The method is based on a variational method, utilizes a prediction rolling optimization idea to train a multilayer feedforward neural network, then uses the multilayer feedforward neural network as an optimization feedback controller to solve an optimization feedback solution of a time-varying multi-input multi-output nonlinear system, and can solve the optimization control problem of the nonlinear system under the condition of moderate calculated amount and occupied storage area capacity. Aiming at a building chilled water cooling type air conditioning system, the invention firstly carries out building air conditioning load prediction, constructs a refrigerating station system prediction model, and determines a prediction control optimization performance index as the sum of squares of deviations between an actual value and an expected value of an Energy Efficiency index EER (Energy Efficiency Ratio) of the refrigerating station system.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (5)
1. A predictive control method for a building air conditioning refrigeration station system is characterized by comprising the following steps: the method comprises the following steps:
1) An optimization layer of the control system optimizes the set value of the controlled parameter of the controller of the field control layer by utilizing a neural network predictive control strategy, and the optimization target is to enable the energy efficiency index EEr of the chilled water system to reach the set value meeting the requirements of cold quantity and energy conservation;
2) Collecting operation data of an air-conditioning refrigeration station system, preprocessing the data, and adopting a composite filtering algorithm, wherein the composite filtering algorithm comprises the following steps: filtering by using a sliding weighted arithmetic mean filtering algorithm and a sliding median mean filtering algorithm;
3) Establishing a load prediction model of the air conditioning system by using a neural network or a support vector machine;
4) Establishing a prediction model of a building air-conditioning refrigeration station system by utilizing a neural network or a support vector machine;
5) Determining the performance index of predictive control optimization of the air conditioning system, namely an objective function:
wherein J (EERr) [ k ]]The method comprises the steps of representing an optimized performance index of an air-conditioning refrigeration station system; m represents the predicted step number; t is t 1 An initial time representing a prediction time domain; EERr [ k ]]The energy efficiency ratio of the air-conditioning refrigeration system at the kth moment is represented; EERr set [k]Representing the set value of the energy efficiency ratio of the air-conditioning refrigeration system at the kth moment;
6) Determining that the neural network prediction controller structure of the building air-conditioning refrigeration station system is a three-layer neural network structure, and the method comprises the following steps:
1) For a system with a single refrigerating machine, a chilled water pump and a cooling water pump running, a control variable chilled water supply water temperature Tchws, a chilled water pump frequency fpum or chilled water flow, a cooling water return water temperature Tcws, a cooling water pump frequency fp or cooling water flow influencing performance indexes are output as a controller and are transmitted to a field controller to be used as a set value of a controlled parameter, and an outdoor temperature Tout, an outdoor relative humidity Rpout, a system cold load Q at the current moment, an EERr set value EERrset and a threshold value-1 are input as the controller;
2) For a system with a plurality of refrigerators, chilled water pumps and cooling water pumps running, the supply water temperature Tchws of a control variable chilled water main supply pipe, the frequency fpumn or the flow rate of chilled water of each chilled water pump, the return water temperature Tcws of a cooling water main return pipe, the frequency fpn of each cooling water pump or the flow rate of cooling water, which influence performance indexes, are output as controllers and are transmitted to a field controller to be used as set values of controlled parameters, wherein subscripts in fpumn and fpn represent the nth chilled water pump or the cooling water pump; taking the outdoor temperature Tout, the outdoor relative humidity Rpout, the system cold load Q at the current moment, the EERr at the current moment, the EERset value EERset and the threshold value-1 as the input of a controller;
7) Carrying out online optimization training on the neural network prediction controller of the building air-conditioning refrigeration station system, carrying out rolling optimization on prediction control according to the following formula to obtain the weight of the neural network controller which enables the optimization objective function to be optimal, thereby obtaining the optimal control quantity:
W＝W+ΔW，
wherein k is any time, x [ k ] is related state variable parameters of the building air-conditioning refrigeration station system at the time k, namely the outdoor temperature, the outdoor relative humidity, the return air temperature, the system cold load and the current EERr, at the current time, wherein the outdoor temperature, the outdoor relative humidity and the return air temperature are measured values, and the system cold load and the current EERr are calculated values according to the electricity consumption and the refrigeration capacity provided by the refrigeration station; x (k + 1) is a set value of EERr at the next time; u [ k ] is the optimal control quantity at k time after the optimization of the neural network prediction controller is finished, namely the set value of the controlled parameter of the controller of the field control layer; u' [ k + i-1] is a control quantity calculated according to the weight of the predictive controller at the last moment in the rolling optimization process; f (-) represents a prediction model of a controlled object, namely a built refrigeration station system neural network prediction model; g (-) represents a neural network controller model; l [ k ] represents the optimized performance index at each moment, namely the deviation square sum between the actual value and the expected value of EERr; λ [ k ] and γ [ k ] represent lagrange multiplier vectors;
8) And repeating the operation in each sampling period, and respectively calculating the control quantity value at each later moment until the control process is finished.
2. The predictive control method for the building air conditioning refrigeration station system as claimed in claim 1, wherein: the EERr is calculated by the following formula:
EERr＝Q ch /P total
wherein P is total The total energy consumption of each equipment of the air-conditioning refrigeration station system is expressed in kW, and can be obtained according to the following formula:
P total ＝P chiller +P pumpch +P pumpc +P tower
wherein P is chiller For water chiller energy consumption, P pumpch For energy consumption of chilled water pumps, P pumpc For cooling water pump energy consumption, P tower Energy consumption for cooling tower;
the energy consumption of the water chilling unit is as follows:
P chiller ＝Q ch /COP
the COP represents the operation energy efficiency of the water chilling unit, and is dimensionless, and Qch is the system cooling load.
3. The predictive control method for the building air conditioning refrigeration station system as claimed in claim 1, wherein: the sliding median average filtering algorithm comprises:
1) Aiming at any J-th original sampling data, the front N-1 original sampling data and the rear N original sampling data form a group of 2N data;
2) Sorting the 2N data;
3) Removing a maximum value and a minimum value before and after the sorted data;
4) Calculating the average value of the residual data, and storing the average value as the J-th sampling data;
5) Then, the J +1 th data is processed in the same way until all the data are processed;
where J and N represent selectable variables that can be modified depending on the actual filtering effect.
4. The predictive control method for the building air conditioning refrigeration station system as claimed in claim 1, wherein: the air conditioning system load prediction model comprises:
1) Air conditioning system load prediction model structure
The input parameter of the prediction model has an outdoor temperature T out Outdoor relative humidity RH out Solar radiation intensity I and outdoor wind speed S north Outdoor wind speed S east The load factor L of the refrigerator, the system cooling load Qch at the current moment, the system cooling load Qch at the same moment before the day- day The cooling load Qch of the system at the same time before the week week The output of the load prediction model is the next time system cold load Q [ k + 1]](ii) a In the above symbols, k represents the current time, and k +1 represents the next time of the current time;
2) Sample data
The sample data is refrigerating station system operation data and outdoor meteorological parameter data in refrigerating season, including outdoor temperature T out Outdoor relative humidity RH out Solar radiation intensity I and outdoor wind speed S north Outdoor wind speed S east The load rate L of the cold machine and the flow rate and the temperature difference of the chilled water supply and return water of the refrigeration station are calculated to obtain a load value, and the load is calculated according to the following formula:
Q ch ＝c·m chw ·(T chwr -T chws )
in the formula, Q ch The system cold load at the current moment, namely the cold quantity prepared by the water chilling unit is expressed in kW unit; c represents the specific heat capacity of water, and the unit kJ/(kg. K); n is a radical of an alkyl radical chw The mass flow of the freezing water is expressed in unit kg/s; t is a unit of chws Represents the temperature of chilled water supply in units; t is a unit of chwr The temperature of the return chilled water is expressed, the unit ℃ and the whole dynamic range of the system are covered by the acquired dataAnd (5) enclosing.
5. The predictive control method for the building air conditioning refrigeration station system as claimed in claim 1, wherein: the building air-conditioning refrigeration station system prediction model comprises the following steps:
1) Determining air-conditioning refrigeration station system prediction model structure
1) For a system with a single refrigerator, chilled water pump, and cooling water pump operating, the prediction model input parameter has chilled water supply temperature T chws Frequency f of the chilled water pump pum Or the flow rate of the freezing water and the return water temperature T of the cooling water cws Frequency f of cooling water pump p Or cooling water flow, outdoor temperature T out Outdoor relative humidity RH out The system cold load Qch at the current moment, the energy efficiency index EERr of the chilled water system at the current moment, and the output of the system load prediction model of the air-conditioning refrigeration station is the next-moment EERr [ k + 1]](ii) a In the above symbols, k represents the current time, and k +1 represents the next time of the current time;
2) For a system with multiple refrigerators, chilled water pumps and cooling water pumps operating, the input parameter of the prediction model is the supply water temperature T of the chilled water main water supply pipe chws Frequency f of each refrigerating water pump pumn Or the flow rate of the freezing water and the return water temperature T of the cooling water main return pipe cws Frequency f of each cooling water pump pn Or cooling water flow, outdoor temperature T out Outdoor relative humidity RH out The system cold load Q at the current moment, the energy efficiency index EERr of the chilled water system at the current moment, and the output of the load prediction model of the air-conditioning refrigeration station system is the EERr [ k + 1] at the next moment](ii) a Wherein f is pumn And f pn The subscript n in the (1) represents the nth refrigerating water pump or cooling water pump;
2) Sample data
1) For a system with a single refrigerating machine, a refrigerating water pump and a cooling water pump operating, the sample data is refrigerating station system operating data and outdoor meteorological parameter data in the refrigerating season, including the supply water temperature T of the refrigerating water chws Frequency f of the chilled water pump pum Or the flow rate of the freezing water and the return water temperature T of the cooling water main return pipe cws Frequency f of cooling water pump p Or cooling water flow, outdoor temperature T out Outdoor relative humidity RH out Return air temperature T in And the flow rate and the temperature difference of the refrigerating water of the refrigerating station, and calculating the load value according to the flow rate and the temperature difference;
2) For a system with a plurality of refrigerators, chilled water pumps and cooling water pumps running, sample data are system running data and outdoor meteorological parameter data of a refrigeration station in a refrigeration season, including water supply temperature T of a chilled water main water supply pipe chws Frequency f of each refrigerating water pump pumn Or the flow rate of the freezing water and the return water temperature T of the cooling water main return pipe cws Frequency f of cooling water pump pn Or cooling water flow, outdoor temperature T out Outdoor relative humidity RH out Return air temperature T in And the flow and the temperature difference of a refrigerating water main pipe of the refrigerating station, and a load value is calculated according to the flow and the temperature difference, and the acquired data cover the whole dynamic range of the system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910589020.XA CN110288164B (en) | 2019-07-02 | 2019-07-02 | Predictive control method for building air-conditioning refrigeration station system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910589020.XA CN110288164B (en) | 2019-07-02 | 2019-07-02 | Predictive control method for building air-conditioning refrigeration station system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110288164A CN110288164A (en) | 2019-09-27 |
| CN110288164B true CN110288164B (en) | 2022-12-02 |
Family
ID=68021699
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910589020.XA Active CN110288164B (en) | 2019-07-02 | 2019-07-02 | Predictive control method for building air-conditioning refrigeration station system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110288164B (en) |
Families Citing this family (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110762768A (en) * | 2019-10-30 | 2020-02-07 | 南京亚派软件技术有限公司 | Energy efficiency ratio prediction method and device for refrigeration host of central air-conditioning system |
| CN110836512A (en) * | 2019-11-14 | 2020-02-25 | 南京亚派软件技术有限公司 | Central air conditioner group control method based on load prediction |
| CN111043731A (en) * | 2019-12-31 | 2020-04-21 | 中维通(北京)科技有限公司 | Air conditioning system adjusting method based on weather forecast |
| CN111240197A (en) * | 2020-01-10 | 2020-06-05 | 中国建筑科学研究院有限公司 | Energy efficiency deviation rectifying control method and device for electromechanical system of public building |
| CN111222191A (en) * | 2020-02-12 | 2020-06-02 | 山东大学 | Building energy consumption optimization control method and system based on BIM and RFID |
| CN111380155B (en) * | 2020-04-02 | 2021-07-27 | 上海市建筑科学研究院有限公司 | Real-time online energy utilization diagnosis method for comprehensive efficiency of cold source operation |
| CN113899055B (en) * | 2020-06-22 | 2023-06-30 | 青岛海信日立空调系统有限公司 | Control system of water chilling unit |
| CN111798045B (en) * | 2020-06-30 | 2023-05-26 | 西安建筑科技大学 | Energy-saving optimization method for chilled water system of central air conditioner |
| CN111928450A (en) * | 2020-07-21 | 2020-11-13 | 国网电力科学研究院武汉能效测评有限公司 | Building energy consumption optimization control method |
| CN112084707A (en) * | 2020-09-02 | 2020-12-15 | 西安建筑科技大学 | Refrigeration machine room energy-saving optimization method and system based on variable flow decoupling of chilled water and cooling water |
| 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 |
| CN113283156B (en) * | 2021-03-29 | 2023-09-15 | 北京建筑大学 | Energy-saving control method for subway station air conditioning system based on deep reinforcement learning |
| CN113821902B (en) * | 2021-06-17 | 2022-07-05 | 李壮举 | Active disturbance rejection control system for static optimization of central air-conditioning refrigeration station |
| CN113268913B (en) * | 2021-06-24 | 2022-02-11 | 广州鼎泰智慧能源科技有限公司 | Intelligent building air conditioner cooling machine system operation optimization method based on PSO-ELM algorithm |
| CN113739360B (en) * | 2021-08-31 | 2022-12-27 | 广州汇电云联互联网科技有限公司 | Energy-saving control method, device, equipment and medium based on multiple intelligent agents of cold station |
| CN113847713B (en) * | 2021-09-27 | 2022-04-12 | 湖南桅灯智能科技有限公司 | Air conditioner water pump energy efficiency diagnosis method and device based on cold quantity and quality |
| CN114234384B (en) * | 2021-12-27 | 2023-08-29 | 中铁第四勘察设计院集团有限公司 | Air conditioning optimization control method and system for railway passenger station |
| CN114440419B (en) * | 2021-12-31 | 2023-10-27 | 博锐尚格科技股份有限公司 | Control method, device, equipment and storage medium of cold station secondary pump system |
| CN114440406B (en) * | 2022-02-28 | 2023-01-06 | 厦门大学 | Air conditioning system control method based on dynamic matrix model predictive control |
| CN114543274B (en) * | 2022-03-15 | 2023-04-11 | 山东大学 | Temperature and humidity optimization control method and system for building central air conditioner |
| WO2023193045A1 (en) * | 2022-04-07 | 2023-10-12 | Exergenics Pty Ltd | A system for controlling chilled water plant |
| CN115560430B (en) * | 2022-09-08 | 2023-05-12 | 金捷利工程技术(北京)有限公司 | Cloud computing-based air conditioner model optimization method and system |
| CN117053355B (en) * | 2023-06-20 | 2024-04-02 | 江苏中屹能源技术有限公司 | Energy-saving control device for refrigerating station and control method thereof |
| CN117743974B (en) * | 2024-02-21 | 2024-05-03 | 武汉船用电力推进装置研究所(中国船舶集团有限公司第七一二研究所) | Method and device for distributing cooling flow of liquid cooling energy storage system and storage medium |
| CN117970986B (en) * | 2024-04-01 | 2024-06-14 | 广东热矩智能科技有限公司 | Temperature and humidity control method, device and medium of cold and hot system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103912966A (en) * | 2014-03-31 | 2014-07-09 | 武汉科技大学 | Optimal control method for ground source heat pump refrigerating system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106338127B (en) * | 2016-09-20 | 2018-06-22 | 珠海格力电器股份有限公司 | For the load prediction of subway heating ventilation air-conditioning system and control system and its method |
-
2019
- 2019-07-02 CN CN201910589020.XA patent/CN110288164B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103912966A (en) * | 2014-03-31 | 2014-07-09 | 武汉科技大学 | Optimal control method for ground source heat pump refrigerating system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110288164A (en) | 2019-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288164B (en) | Predictive control method for building air-conditioning refrigeration station system | |
| CN108990383B (en) | Predictive control method for air conditioning system of data center | |
| CN108413567B (en) | Central air conditioner cost-saving optimization method and system based on Internet of things | |
| CN100362295C (en) | Automatic volume regulating and controlling method for gas-burning machine heat pump | |
| CN110392515A (en) | A kind of Cooling and Heat Source equipment room energy-conserving control method and system based on historical data | |
| CN105571073B (en) | A kind of subway station air-conditioner water system frequency conversion control energy-saving method | |
| CN110895016A (en) | Fuzzy self-adaptive based energy-saving group control method for central air-conditioning system | |
| CN105605753B (en) | Fresh air air-supply temperature control system based on multi-connected machine and new blower fan composite air conditioner system | |
| CN201666640U (en) | Control system of central air conditioner based on wireless sensor network | |
| CN101968250A (en) | Energy-saving optimized control system and method for refrigerator room | |
| CN110410942A (en) | A kind of Cooling and Heat Source machine room energy-saving optimal control method and system | |
| CN110107989A (en) | Small-sized based on chilled water return water temperature optimum set point determines frequency water cooler and becomes temperature control method of water | |
| CN105444356A (en) | Intelligent energy efficiency optimizing control system for central air conditioning system and control method of intelligent energy efficiency optimizing control system | |
| CN210320428U (en) | Energy-saving intelligent control system combining central air conditioner and central heating | |
| CN115220351B (en) | Intelligent energy-saving optimization control method for building air conditioning system based on cloud side end | |
| CN100434822C (en) | Cold volume governing system for regionally concentrated cold supply second-stage cold volume exchange station | |
| CN116398994B (en) | Water chilling unit group control optimization method based on load prediction | |
| CN113446661B (en) | Intelligent and efficient heat supply network operation adjusting method | |
| CN116857863B (en) | Multi-energy complementary system optimal control method and device based on large-scale ground source heat pump | |
| CN110486896B (en) | Cascade air conditioning system optimization control method based on water chilling unit energy consumption model | |
| CN201944984U (en) | Energy-saving optimization control system of refrigerator room | |
| CN113218040A (en) | Energy efficiency improvement control method for central air-conditioning system | |
| CN111415036B (en) | Load optimization distribution method for parallel connection cold machines of central air-conditioning system | |
| CN210441402U (en) | Automatic control device of air conditioning system | |
| CN116227342A (en) | Regional cooling system cold station optimization algorithm based on simulation and cold load prediction model |
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 |