CN104833154B - Chilled water loop control method based on fuzzy PID and neural internal model - Google Patents

Chilled water loop control method based on fuzzy PID and neural internal model Download PDF

Info

Publication number
CN104833154B
CN104833154B CN201510283600.8A CN201510283600A CN104833154B CN 104833154 B CN104833154 B CN 104833154B CN 201510283600 A CN201510283600 A CN 201510283600A CN 104833154 B CN104833154 B CN 104833154B
Authority
CN
China
Prior art keywords
chilled water
control
neural network
internal model
layer
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
Application number
CN201510283600.8A
Other languages
Chinese (zh)
Other versions
CN104833154A (en
Inventor
白建波
李洋
罗朋
彭俊
王孟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanxi Fengyun Haitong Technology Co ltd
Original Assignee
Changzhou Campus of Hohai University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Changzhou Campus of Hohai University filed Critical Changzhou Campus of Hohai University
Priority to CN201510283600.8A priority Critical patent/CN104833154B/en
Publication of CN104833154A publication Critical patent/CN104833154A/en
Application granted granted Critical
Publication of CN104833154B publication Critical patent/CN104833154B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • F24F11/70—Control systems characterised by their outputs; Constructional details thereof
    • F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
    • F24F11/83—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling the supply of heat-exchange fluids to heat-exchangers
    • 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
    • F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
    • 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
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
    • F25B—REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
    • F25B41/00—Fluid-circulation arrangements
    • F25B41/40—Fluid line arrangements
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
    • F25B—REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
    • F25B49/00—Arrangement or mounting of control or safety devices
    • F25B49/02—Arrangement or mounting of control or safety devices for compression type machines, plants or systems
    • F25B49/022—Compressor control arrangements
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/50—Control or safety arrangements characterised by user interfaces or communication
    • F24F11/56—Remote control
    • F24F11/59—Remote control for presetting
    • 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
    • F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
    • F25B—REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
    • F25B2600/00—Control issues
    • F25B2600/02—Compressor control
    • F25B2600/025—Compressor control by controlling speed

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Physics & Mathematics (AREA)
  • Thermal Sciences (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Signal Processing (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

The invention discloses a chilled water loop control method based on a fuzzy PID and a neural internal model. An air conditioner performs real-time control over a compressor through the method after collecting the water outlet temperature of chilled water, wherein the compressor is a controlled object in a chilled water loop. The method includes the steps that step1, a target value of the controlled object is set; step2, a fuzzy PID controller and a neural network estimator together form internal model control; step3, the controlled object is trained through the neural network estimator to be a controlled object model in an ideal state; step4, deviation is adjusted through the fuzzy PID controller, finally, self-adaptation control over the chilled water loop of a variable-air-volume air conditioner system is achieved, and stable output of the controlled object is achieved. The fuzzy PID and the neural internal model control are combined, the defects of nonlinearity and time varying in the chilled water loop can be overcome, and accurate and rapid control is achieved.

Description

Based on fuzzy and the chilled water circuit control method of neural internal model
Technical field
The present invention relates to it is a kind of based on fuzzy and the chilled water circuit control method of neural internal model, belong to variable air rate empty Conditioning technology field.
Background technology
Since the sixties in 20th century, air conditioning system with variable is born in the U.S., due to its energy-conservation, it is comfortable the features such as it is wide It is general to be applied to various Working Life places, but due to the aggravation of energy crisis so that there is a growing awareness that necessity of energy-conservation Property.As the natural attention due to having attracted numerous scholars of the air conditioning system with variable that main status is occupied in building energy consumption, The humiture that the final purpose of air conditioning system with variable is so that in room reaches the requirement of people, therefore how to meet people Comfort level realizes that the Energy Saving Control of air conditioning system becomes the hot issue of current field of air conditioning on the premise of requiring.
It is well known that wind circulation and two parts of water circulation in air conditioning system with variable, can be divided into, and chilled water circuit Important component part exactly in water circulation, chilled water are entering surface cooler and the air that will be fed into room after vaporizer Heat exchange is carried out, and indoor air themperature is adjusted by controlling wind pushing temperature, is finally reached the requirement for meeting people's comfort level.Cause This chilled water is particularly important in air conditioning system with variable in the leaving water temperature after vaporizer, but as chilled water is returned The features such as road has non-linear, time-varying, conventional control mode can not play good control effect.
The content of the invention
This invention proposes a kind of chilled water circuit control method based on fuzzy and neural internal model, by fuzzy Combine with Neural network internal model control, the features such as the non-linear, time-varying in chilled water circuit can be overcome, realize accurately and rapidly Control purpose.
Technical scheme is as follows：
A kind of air quantity variable air conditioner chilled water leaving water temperature control method based on fuzzy and Neural network internal model control, which is special It is, after air-conditioning collects chilled water leaving water temperature, real-time control to be carried out to compressor by method to levy, and compressor is chilled water Controlled device in loop, methods described comprise the steps：
(1), set desired value y of controlled deviceset；
(2), fuzzy controller and neural network estimator collectively form internal model control；
(3), controlled device becomes plant model ideally through the training of neural network estimator；
(4), when mismatch occurs in controlled device or receives external disturbance d, the measured value y of chilled water leaving water temperature and freezing Setting value y of water leaving water temperaturemBetween can produce deviation delta y, this deviation is imported into the input of chilled water control loop, then is led to Fuzzy controller is crossed for deviation e, deviation e is desired value ysetWith the difference of deviation delta y, it is adjusted, it is final to realize becoming wind The Self Adaptive Control of amount air conditioning system chilled water circuit, realizes that controlled device is stably exported.
In above-mentioned steps (3), neural network estimator uses BP neural network, using three-layer network, i.e. input layer, implies Layer, output layer；Calculation procedure is：
(21), initialize：All of connection weight coefficient is entered as into the random number of minimum；
(22), it is trained using the input value of the ideal model of chilled water circuit；
(23), calculate the reality output of neutral net；
(24), calculate deviation delta y of the reality output of the expected value and neutral net of ideal model；
(25), adjust the weight coefficient w of output layerki；
(26), adjust the weight coefficient w of hidden layerij；
(27) the 23rd step is returned, till deviation delta y meets requirement.
The beneficial effect reached by the present invention：
Fuzzy controller is combined by the present invention with internal model control, applies the freezing water control in air conditioning system with variable In loop processed, both advantages are taken full advantage of, the features such as non-linear, time-varying in air conditioning system can be overcome, fast and accurately Control compressor horsepower, maintains wind pushing temperature in setting value, and the final comfortableness for causing air-conditioned room to disclosure satisfy that people is required.
There is advantages below compared to the control mode in traditional chilled water leaving water temperature loop：
1. non-linear, the time-varying characteristics of air conditioning system can be overcome；
2. fuzzy controller and neural network estimator all have certain adaptive ability, can be in extraneous appearance Stablizing for control system is maintained during random disturbance；
3. the parameter tuning problem of traditional PID control is avoided；
4. as final controlled device is compressor, so larger section will be produced using the control algolithm in the present invention Can effect.
Description of the drawings
Fig. 1 is air conditioning system with variable chilled water circuit；
Fig. 2 is the schematic diagram of chilled water circuit control method；
Fig. 3 is the workflow diagram of the inventive method；
Fig. 4 is the structure chart of BP neural network.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.Following examples are only used for clearly illustrating the present invention Technical scheme, and can not be limited the scope of the invention with this.
As shown in figure 1, the chilled water circuit in air conditioning system with variable includes that vaporizer, chilled water pump, surface cooler etc. are more Individual link, main operation principle are, after chilled water leaving water temperature is set, can to adjust the power of compressor, are maintained cold Freeze water effluent temperature constancy, and then wind pushing temperature is able to maintain that in setting value, it is ensured that air conditioning system can be stablized, continuously be transported OK.Additionally due to the power of compressor is adjusted, the effect of energy-conservation has also been further functioned as.Chilled water circuit control algolithm The chilled water leaving water temperature that collects of needs, and real-time control is carried out to compressor, it is seen that real controlled in chilled water circuit Object is compressor.According to engineering experience, the chilled water leaving water temperature control loop in air conditioning system is usually used with delay The first order inertial loop of link is used as transmission function.
In engineering in practice, the load variations of air conditioning system with variable can embody the change of air output and wind pushing temperature On, and chilled water and the air directly contact for sending into room, therefore the size of chilled water leaving water temperature changing value similarly can be with The size of load variations is represented, the control to chilled water leaving water temperature in system is to change to realize by the frequency of compressor 's.
As shown in Figure 2 and Figure 3, a kind of chilled water circuit control method based on fuzzy and neural internal model, including it is as follows Step：
(1), set desired value y of controlled deviceset；
(2), fuzzy controller and neural network estimator collectively form internal model control；
(3), controlled device becomes plant model ideally through the training of neural network estimator；
(4), when mismatch occurs in controlled device or receives external disturbance d, the measured value y of chilled water leaving water temperature and freezing Setting value y of water leaving water temperaturemBetween can produce deviation delta y, this deviation is imported into the input of chilled water control loop, then is led to Fuzzy controller is crossed for deviation e, deviation e is desired value ysetWith the difference of deviation delta y, it is adjusted, it is final to realize becoming wind The Self Adaptive Control of amount air conditioning system chilled water circuit, realizes that controlled device is stably exported.
In above-mentioned steps (3), the training of neural network estimator is as follows：
The neural network estimator adopted in this invention uses relatively common BP neural network, using three-layer network, That is input layer, hidden layer, output layer, as BP neural network is a kind of training algorithm of utilization error back propagation, constantly The connection weight of each layer is adjusted, the accurate characteristic of description preferable controlled device the features such as finally overcome non-linear.
The ultimate principle of BP neural network learning algorithm is gradient steepest descent method, using gradient search technology, makes network The error mean square difference of real output value and desired output be minimum, in running, while Feedback error, finishing connects Connect weights.
The structure of BP neural network is as shown in Figure 4.Can see there be M input node in Fig. 4, L output node, network Hidden layer have q neuron, wherein x1、x2、…、xmThe respectively input of BP neural network, y1、y2、…、yLIt is neural for BP The output of network, ysetTarget for neutral net is exported, ekFor the output error of neutral net.
In the study stage of training network, ideal model of the controlled device using chilled water circuit：
K, T in formula1Respectively proportionality coefficient and time constant, τ then represent delay, the chilled water circuit in air conditioning system Ideal model is the one order inertia transmission function with pure delay link, and this model is chosen at current airconditioning control field Gain public acceptance.
Assume that neutral net can accurately represent the ideal model, first take one of sample after N number of training sample The input of this P, output mode are trained to network, and input of i-th neuron of hidden layer under sample p effects is：
In formulaWithRespectively input and output of input node j under sample p effects, due to the activation letter of input layer Number is 1, for the node of input layer is equal；wijIt is the connection weight between input node j and hidden layer neuron i, its Middle i=1,2 ..., q；θiFor the threshold value of hidden layer neuron i；Quantity of the M for input layer；
I-th neuron of hidden layer is output as：
Activation primitives of the g () for hidden layer in formula, from Sigmoid functions, i.e.,：
To hidden layer activation primitiveCan obtain after differentiating：
The output of i-th neuron of hidden layerK-th neuron of output layer will be traveled to forward by weight coefficient to make One of input for him, total input of k-th neuron of output layer is：
K=1 in formula, 2 ..., L, wkiFor the connection weight between hidden layer neuron i and output layer neuron k；θkIt is defeated Go out a layer threshold value of neuron k；Q is the nodes of hidden layer；
The reality output of k-th neuron of output layer is：
Output layer activation primitiveDifferentiation function be：
If output valve y of the output valve of the output layer of neutral net and ideal modelkIt is inconsistent, then it is deviation signal is reverse Propagation is returned, and the connection weight dripped between each layer more is adjusted, and on output layer neuron obtains desired output valve Till, and known sample is trained one by one, till completing the training of N number of sample.
The error function produced by input pattern for arbitrary sample p is：
Then for the total error function of all of N number of sample is：
As error is back transfer, so the adjustment of connection weight is by output layer so that neutral net is final Convergence.According to gradient descent method, the neuron connection weight finishing formula of output layer is：
In formula η be learning rate, η ＞ 0.
Definition
Therefore the correction formula of the connection weight of any neuron k of output layer is：
In formulaRepresent outputs of the output node k when sample p is acted on；Represent hidden layer node i when sample p is acted on Output；ykRepresent the target output value of the output node k when sample p is input into.
According to gradient descent method, can learn that the correction formula of hidden layer each neuron connection weight is：
In formula η be learning rate, η ＞ 0.
Definition
As the change of a unit output of hidden layer can affect the defeated of all output units being connected with the unit Enter, i.e.,
ThenTherefore the connection weight correction formula of any neuron i of hidden layer is：
In formula,For outputs of the hidden layer node i when sample p is acted on；For input node j when sample p is acted on Output, the i.e. input of input node j.
It can be seen that in the learning process of BP neural network, make error function J adjust connection weight along most fast direction is declined, Any neuron k and i of output layer and hidden layer increment formula of connection weight in the presence of all samples can be obtained is：
The calculation procedure of BP neural network estimator is：
A. initialize：All of connection weight coefficient is entered as into the random number of minimum；
B. it is trained using the input value of the ideal model of chilled water circuit；
C. calculate the reality output of neutral net；
D. the expected value of ideal model and deviation delta y of the reality output of neutral net are calculated；
E. adjust the weight coefficient w of output layerki；
F. adjust the weight coefficient w of hidden layerij；
G. the 3rd step is returned, till error meets requirement.
Fuzzy-adaptation PID control in step (4), compared with regulatory PID control mode, with regulating time it is short, steady-state behaviour is good, The advantages of strong robustness, the change of air conditioning system load can be better adapted to.The Fuzzy Adaptive PID Control of present invention design Device structure exists《CN201410403382- is based on fuzzy and the variable air rate room temp. control method with predictive control algorithm》In have Record in detail, the present invention is not described in detail.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art For member, on the premise of without departing from the technology of the present invention principle, some improvement and deformation can also be made, these improve and deform Also should be regarded as protection scope of the present invention.

Claims (2)

1. a kind of chilled water circuit control method based on fuzzy and neural internal model, it is characterised in that air-conditioning collects freezing After water leaving water temperature, real-time control is carried out by method to compressor, compressor is the controlled device in chilled water circuit, described Method comprises the steps：
(1), set desired value y of controlled deviceset；
(2), fuzzy controller and neural network estimator collectively form internal model control；
(3), controlled device becomes plant model ideally through the training of neural network estimator；
(4), when mismatch occurs in controlled device or receives external disturbance d, the measured value y of chilled water leaving water temperature and chilled water go out Setting value y of coolant-temperature gagemBetween can produce deviation delta y, this deviation is imported into the input of chilled water control loop, then by mould Paste PID controller is adjusted for deviation e, and deviation e is desired value ysetWith the difference of deviation delta y, air quantity variable air conditioner is finally realized The Self Adaptive Control of system chilled water circuit, realizes that controlled device is stably exported.
2. the chilled water circuit control method based on fuzzy and neural internal model according to claim 1, it is characterised in that In the step (3), neural network estimator uses BP neural network, using three-layer network, i.e. input layer, hidden layer, output Layer；Calculation procedure is：
(21), initialize：All of connection weight coefficient is entered as into the random number of minimum；
(22), it is trained using the input value of the ideal model of chilled water circuit；
(23), calculate the reality output of neutral net；
(24), calculate deviation delta y of the reality output of the expected value and neutral net of ideal model；
(25), adjust the weight coefficient w of output layerki；
(26), adjust the weight coefficient w of hidden layerij；
(27) the 23rd step is returned, till deviation delta y meets requirement.
CN201510283600.8A 2015-05-28 2015-05-28 Chilled water loop control method based on fuzzy PID and neural internal model Active CN104833154B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510283600.8A CN104833154B (en) 2015-05-28 2015-05-28 Chilled water loop control method based on fuzzy PID and neural internal model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510283600.8A CN104833154B (en) 2015-05-28 2015-05-28 Chilled water loop control method based on fuzzy PID and neural internal model

Publications (2)

Publication Number Publication Date
CN104833154A CN104833154A (en) 2015-08-12
CN104833154B true CN104833154B (en) 2017-04-12

Family

ID=53811208

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510283600.8A Active CN104833154B (en) 2015-05-28 2015-05-28 Chilled water loop control method based on fuzzy PID and neural internal model

Country Status (1)

Country Link
CN (1) CN104833154B (en)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105759607B (en) * 2016-02-26 2018-08-14 北京工业大学 The design method of PAC controllers based on intelligent control algorithm
CN106765863B (en) * 2016-11-14 2019-10-01 华北电力大学（保定） A kind of temperature and humidity Universal logic intelligent control method for convertible frequency air-conditioner
CN106849082B (en) * 2017-03-10 2019-06-11 国网江苏省电力公司常州供电公司 The Research on Unified Power Quality Conditioner Harmonic Control Method of the power distribution network containing photovoltaic
CN108361923A (en) * 2018-03-02 2018-08-03 山东三江电子工程有限公司 The prediction technique of central air-conditioning water returning temperature stationary value
CN109612049B (en) * 2018-11-13 2021-03-16 上海冷元节能科技有限公司 Method and device for controlling output power of compressor
CN109597449A (en) * 2019-01-30 2019-04-09 杭州庆睿科技有限公司 A kind of ultrasonic wave separating apparatus temprature control method neural network based
CN109905487A (en) * 2019-03-20 2019-06-18 辽宁工业大学 A kind of intelligent health management system and method based on cloud computing
CN111306695B (en) * 2019-12-04 2021-08-24 珠海格力电器股份有限公司 Compressor load data optimization method and device, computer equipment and storage medium
CN114413613B (en) * 2021-12-27 2023-03-21 广西电网有限责任公司电力科学研究院 Multi-physical-field decoupling control method and system for air source heat pump drying system
CN117329665B (en) * 2023-10-16 2024-04-12 珠海珠江建筑设计院有限公司 Air conditioner indoor linkage control method and system based on intelligent AI algorithm

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0510568A (en) * 1991-07-05 1993-01-19 Toshiba Corp Air conditioner
JP2000274862A (en) * 1999-03-23 2000-10-06 Sanyo Electric Co Ltd Temperature controller for absorption refrigerator
KR20110116672A (en) * 2010-04-20 2011-10-26 김두일 Ventiation system for aparatment house using solar cell module
CN101782261B (en) * 2010-04-23 2012-01-11 吕红丽 Nonlinear self-adapting energy-saving control method for heating ventilation air-conditioning system
CN104019520B (en) * 2014-05-20 2017-01-18 天津大学 Data drive control method for minimum energy consumption of refrigerating system on basis of SPSA
CN104534627B (en) * 2015-01-14 2017-03-15 江苏联宏自动化系统工程有限公司 Central air conditioning cooling water system comprehensive energy efficiency control method

Also Published As

Publication number Publication date
CN104833154A (en) 2015-08-12

Similar Documents

Publication Publication Date Title
CN104833154B (en) Chilled water loop control method based on fuzzy PID and neural internal model
CN110288164B (en) Predictive control method for building air-conditioning refrigeration station system
CN111256294B (en) Model prediction-based optimization control method for combined operation of water chilling unit
CN109270842B (en) Bayesian network-based regional heat supply model prediction control system and method
CN104019526B (en) Improve PSO algorithm Fuzzy Adaptive PID temperature and humidity control system and method
He et al. Multiple fuzzy model-based temperature predictive control for HVAC systems
CN102353119B (en) Control method of VAV (variable air volume) air-conditioning system
CN113283156B (en) Energy-saving control method for subway station air conditioning system based on deep reinforcement learning
CN104154635B (en) Variable air rate room temp. control method based on fuzzy Yu predictive control algorithm
CN104534627B (en) Central air conditioning cooling water system comprehensive energy efficiency control method
CN104019520B (en) Data drive control method for minimum energy consumption of refrigerating system on basis of SPSA
CN109945402A (en) A kind of central air conditioning water system power-economizing method
CN101968629A (en) PID (Proportional Integral Derivative) control method for elastic integral BP neural network based on RBF (Radial Basis Function) identification
CN111365828A (en) Model prediction control method for realizing energy-saving temperature control of data center by combining machine learning
CN101498534A (en) Multi-target intelligent control method for electronic expansion valve of refrigeration air conditioner heat pump system
CN105790286B (en) A kind of central air-conditioning load polymerization and the strategy for participating in stabilizing distributed generation resource output
CN102734890B (en) Fuzzy control method and device for chilled water of central air-conditioning and central air-conditioning system
CN104834215A (en) Variation particle swarm optimized BP neural network proportion integration differentiation (PID) control algorithm
CN105843037A (en) Q-learning based control method for temperatures of smart buildings
CN109612055A (en) A kind of feedforward fuzzy control method of air-conditioner water system
CN111415036B (en) Load optimization distribution method for parallel connection cold machines of central air-conditioning system
CN117093033A (en) Resistance heating furnace temperature control system for optimizing PID parameters based on particle swarm optimization
Li et al. HVAC room temperature prediction control based on neural network model
CN106230002A (en) A kind of air conditioner load demand response method based on index rolling average
CN104949274B (en) A kind of air quantity variable air conditioner handpiece Water Chilling Units double loop control method

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
EXSB Decision made by sipo to initiate substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20200416

Address after: 044000 Room 101, building a, Guanghui company, Nanfeng Industrial Park, Yuncheng Economic Development Zone, Yanhu District, Yuncheng City, Shanxi Province

Patentee after: Shanxi Fengyun Haitong Technology Co.,Ltd.

Address before: 213022 Changzhou campus, Hohai University, 200 North Ling Road, Jiangsu, Changzhou

Patentee before: CHANGZHOU CAMPUS OF HOHAI University

TR01 Transfer of patent right