CN111678279A - Model for predicting optimal defrosting control point of air source heat pump and establishing method thereof - Google Patents

Model for predicting optimal defrosting control point of air source heat pump and establishing method thereof Download PDF

Info

Publication number
CN111678279A
CN111678279A CN202010445957.2A CN202010445957A CN111678279A CN 111678279 A CN111678279 A CN 111678279A CN 202010445957 A CN202010445957 A CN 202010445957A CN 111678279 A CN111678279 A CN 111678279A
Authority
CN
China
Prior art keywords
heat pump
source heat
air source
control point
defrosting control
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010445957.2A
Other languages
Chinese (zh)
Inventor
王伟
李昭阳
孙育英
王世权
吴旭
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.)
Beijing University of Technology
Original Assignee
Beijing University of Technology
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 Beijing University of Technology filed Critical Beijing University of Technology
Priority to CN202010445957.2A priority Critical patent/CN111678279A/en
Publication of CN111678279A publication Critical patent/CN111678279A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • 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
    • F25B47/00—Arrangements for preventing or removing deposits or corrosion, not provided for in another subclass
    • F25B47/02—Defrosting cycles
    • 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
    • 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
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Mechanical Engineering (AREA)
  • Thermal Sciences (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

A model for predicting an optimal defrosting control point of an air source heat pump and an establishing method thereof belong to the field of defrosting control of the air source heat pump. Measuring the heating capacity loss of the unit when the air source heat pump operates under the frosting working condition by taking the nominal heating capacity of the air source heat pump as a reference; determining an influence relation among a frosting working condition, a unit frosting operation time and an evaluation index by utilizing a generalized artificial neural network GRNN method, and simulating the heating loss of the unit under different frosting working conditions by adopting different defrosting control points; based on the simulation result, confirming the defrosting control point corresponding to the minimum heating loss under the same frosting working condition as the optimal defrosting control point of the air source heat pump under the frosting working condition, and establishing an optimal defrosting control point database of the air source heat pump under the full working condition according to the method; and (3) constructing a function relation between the optimal defrosting control point and the frosting working condition by utilizing a multiple nonlinear equation regression method, and establishing an optimal defrosting control point prediction model of the air source heat pump.

Description

Model for predicting optimal defrosting control point of air source heat pump and establishing method thereof
Technical Field
The invention relates to a model for predicting an optimal defrosting control point of an air source heat pump and an establishing method thereof, belonging to the field of defrosting control of the air source heat pump.
Technical Field
Frosting is a key problem affecting the operating efficiency of the air source heat pump unit. Due to the existence and growth of the frost layer, the heat transfer resistance of the outdoor heat exchanger of the air source heat pump unit is increased, the heat transfer coefficient is reduced, the air flow resistance is increased, and the heating capacity of the unit is reduced, so that the defrosting control must be carried out on the unit. The ideal defrost is a "defrost on demand" process that includes: sensing existence of frost layer; monitoring the growth of the frost layer; judging the optimal defrosting control point; and fourthly, defrosting. However, frosting is a complex heat and mass transfer process, the existing defrosting control method can only sense the existence of a frost layer or monitor the growth of the frost layer, systematic research on an optimal defrosting control point is lacked, and the setting of the defrosting control point only depends on experience or experimental judgment, so that the unit is difficult to defrost at a proper defrosting time in actual operation, thereby causing frequent 'wrong defrosting' accidents, and further deteriorating the operation efficiency of the air source heat pump unit.
The optimal defrosting control point refers to the optimal defrosting time of the air source heat pump in the defrosting operation process, so that the heating loss of the unit in the periodic defrosting cycle is minimum. In the periodic defrosting process, if the defrosting time of the unit is earlier, the defrosting times in unit time are increased, and the defrosting loss of the unit is increased; on the other hand, if the defrosting is late, the frost loss of the unit is increased due to the accumulation of a large amount of frost as the frost running time is increased. Therefore, whether the optimal defrosting control point of the air source heat pump can be accurately judged is the key for avoiding the occurrence of the 'wrong defrosting' accident of the air source heat pump and improving the actual operation performance of the unit.
Disclosure of Invention
The invention aims to: the model is used for predicting the optimal defrosting control point of the air source heat pump, and the establishment method is provided, so that the optimal defrosting control point of the air source heat pump running under different frosting working conditions can be effectively predicted through the model, and theoretical support is provided for the efficient defrosting control of the air source heat pump.
In order to achieve the purpose, the technical scheme of the invention is as follows: a method for establishing a model for predicting an optimal defrosting control point of an air source heat pump comprises the following steps:
(1) taking the nominal heating capacity of the air source heat pump as a reference, providing a performance evaluation index of the air source heat pump in the defrosting operation process, and measuring the heating capacity loss of the unit when the air source heat pump operates under the frosting working condition by using the index;
(2) determining the influence relationship among the frosting working condition, the unit frosting operation time and the evaluation index provided in the step (1) by utilizing a generalized artificial neural network (GRNN) method, establishing a GRNN model, and simulating the heating loss of the unit adopting different defrosting control points under different frosting working conditions;
(3) based on the GRNN model simulation result, confirming the defrosting control point corresponding to the minimum heating loss under the same frosting working condition as the optimal defrosting control point of the air source heat pump under the frosting working condition, and establishing an optimal defrosting control point database of the air source heat pump under the full working condition according to the method;
(4) and constructing a function relation between the optimal defrosting control point and the frosting working condition by utilizing a multiple nonlinear equation regression method based on the optimal defrosting control point database, thereby establishing an optimal defrosting control point prediction model of the air source heat pump.
Furthermore, in the step (1), the performance evaluation index of the air source heat pump junction defrosting operation process is a nominal heating loss coefficient,NLthe physical meaning of the method is the ratio of the sum of the frosting heating loss and the defrosting heating loss to the total nominal heating capacity of the unit in the single defrosting circulation process of the air source heat pump.
In the step (2), the GRNN model is established by training the operation data of the air source heat pump unit in the heating season of the year, and the relative error of the simulation data is within +/-10%.
In the step (3), the optimal defrosting control point database comprises the optimal defrosting control points of the air source heat pump under the working conditions that the environmental temperature is-15-6 ℃ (the interval is 1 ℃) and the relative humidity is 50-100% (the interval is 1%).
In the step (4), the optimal defrosting control point prediction model established only inputs frosting condition parameters (environment temperature and environment humidity), and can output the optimal defrosting control point of the air source heat pump under the condition.
The invention has the beneficial effects that: (1) the optimal defrosting control point of the air source heat pump under different frosting working conditions can be judged quickly and effectively; (2) the model has good applicability and is not limited by regions and meteorological conditions; and (3) guidance is provided for improvement and development of a defrosting control method, and the occurrence of 'wrong defrosting' accidents is avoided.
Drawings
FIG. 1 is a schematic diagram of the nominal heating loss coefficient of the air source heat pump according to the present invention, wherein QL1-nominal frost loss (kJ); qL2-nominal defrost loss (kJ); t is ti-a frosting run time or defrosting control point(s); t is tn-defrost end time(s); q. q.shc-nominal heating capacity (kW); q. q.shc2-actual heat production (kW);
FIG. 2 is a generalized artificial neural network (GRNN) model structure diagram established by the present invention, the structure diagram is composed of four links of an input layer, a mode layer, a summation layer and an output layer, the environmental temperature, the relative humidity and the frosting operation time of the unit are used as input parameters, and the nominal heating loss coefficient is used as an output parameter;
fig. 3 is a prediction model of the optimal defrosting control point of the air source heat pump established by the invention, and the model can determine the optimal defrosting control point of the air source heat pump through the ambient temperature and the relative humidity, namely, the unit performs defrosting control after the frosting operation reaches the time point under the working condition.
Detailed Description
The following describes a model for predicting an optimal defrost control point of an air source heat pump and a method for establishing the same according to the present invention with reference to the accompanying drawings, but the present invention is not limited to the following embodiments.
Example 1
And establishing an optimal defrosting control point model aiming at a certain air source heat pump.
(1) Referring to FIG. 1, nominal heating loss coefficient of air source heat pump junction defrosting operation processNLCan be calculated as follows:
nominal frost loss:
Figure RE-GDA0002617667240000031
nominal defrost loss:
Figure RE-GDA0002617667240000032
nominal heating loss coefficient:
Figure RE-GDA0002617667240000033
(2) with reference to fig. 2, based on the principle of GRNN neural network, the air source heat pump is trained to adopt 362 sets of operation data of different defrosting control points under different frosting conditions. Wherein:
(ii) an input layer
The input layer has 3 neurons, i.e. the ambient temperature TaRelative humidity RH and frosting run time tiEach neuron is a simple distribution unit that can directly pass input parameters to the mode layer.
Mode layer
The pattern layer has 362 neurons, i.e., 362 training samples. The model selects a Gaussian function as a transfer function form, and the output expression of the nth neuron of the mode layer is as follows:
Figure RE-GDA0002617667240000034
‖X-Xnthe input of |' is neuron is network input vector X and weight vector XnEuclidean distance of. When the input of the neuron is 0, the output of the neuron is a maximum value of 1. The sensitivity of neurons to input is regulated by the smoothing factor σ.
③ summation layer
The summation layer includes two types of neurons, the first type of neuron computationally sums the neuron outputs of all mode layers, and the transfer function is:
Figure RE-GDA0002617667240000041
the second type of neuron is to perform weighted summation on the outputs of all mode layers, and the weight is the output Y of the nth training samplenThe j-th element of (1), the transfer function is:
Figure RE-GDA0002617667240000042
output layer
The output layer has 1 neuron, i.e. the nominal heating loss coefficientNLEach neuron divides the output of the summation layer to obtain a prediction result, and the output of the jth neuron corresponds to the prediction result of the jth element, and the prediction result is as follows:
Figure RE-GDA0002617667240000043
determining that the optimal smoothing factor sigma of the GRNN prediction model is 0.10 and the cross validation error EEP is 3.45% by adopting a cross validation method, and simulating the nominal heating loss coefficient of the unit by adopting different defrosting control points under different frosting working conditions through the GRNN modelNLThe relative error of the data is within +/-10%;
(3) respectively simulating the environmental temperature T based on the GRNN prediction modelaAt the working condition of-15-6 ℃ (interval of 1 ℃), the relative humidity RH is at the unit frosting operation time t under the working condition of 50-100% (interval of 1%) (RH)iA nominal heating loss coefficient of 20-60 min (interval of 1min)NLTotalizing 138006 groups of data, and determining the defrosting control point corresponding to the minimum nominal heating loss coefficient under the same frosting condition as the optimal defrosting control point t of the air source heat pump under the frosting conditionoptEstablishing the optimal defrosting control point t under the all working conditions of the air source heat pump according to the methodoptA database;
(4) based on the optimal defrost control point t, see FIG. 3optDetermining independent variable environment temperature T by using multiple nonlinear equation regression methodaAnd relative humidity RH, carrying out correlation analysis and significance test on influencing factors through SPSS data processing software, respectively carrying out unitary curve estimation on independent variables, determining an optimal curve form, and then recombining through a multivariate binomial method to obtain a multivariate nonlinear equation. Stepwise regression analysis is carried out on the multiple nonlinear equation to eliminate non-significant explanatory variables, then multiple collinearity of the equation is eliminated through a principal component analysis method, and finally an optimal defrosting control point prediction model of the air source heat pump is established, wherein the model regression equation is as follows:
Figure RE-GDA0002617667240000051
the on-site actual measurement verifies that the optimal defrosting control point prediction model provided by the invention can accurately determine the optimal defrosting time of the air source heat pump under different frosting working conditions, the relative model prediction error is within +/-5.0%, theoretical support is provided for the high-efficiency defrosting control technology of the air source heat pump, and the occurrence of 'wrong defrosting' accidents is effectively avoided.

Claims (7)

1. A method for establishing a model for predicting an optimal defrosting control point of an air source heat pump is characterized by comprising the following steps:
(1) taking the nominal heating capacity of the air source heat pump as a reference, providing a performance evaluation index of the air source heat pump in the defrosting operation process, and measuring the heating capacity loss of the unit when the air source heat pump operates under the frosting working condition by using the index;
(2) determining the influence relationship among the frosting working condition, the unit frosting operation time and the evaluation index provided in the step (1) by utilizing a generalized artificial neural network (GRNN) method, establishing a GRNN model, and simulating the heating loss of the unit adopting different defrosting control points under different frosting working conditions;
(3) based on the GRNN model simulation result, confirming the defrosting control point corresponding to the minimum heating loss under the same frosting working condition as the optimal defrosting control point of the air source heat pump under the frosting working condition, and establishing an optimal defrosting control point database of the air source heat pump under the full working condition according to the method;
(4) and constructing a function relation between the optimal defrosting control point and the frosting working condition by utilizing a multiple nonlinear equation regression method based on the optimal defrosting control point database, thereby establishing an optimal defrosting control point prediction model of the air source heat pump.
2. The method for building a model for predicting the optimal defrosting control point of an air source heat pump according to claim 1, wherein in the step (1), the performance evaluation index of the defrosting operation process of the air source heat pump junction is a nominal heating loss coefficient,NLthe physical meaning of the method is the ratio of the sum of the frosting heating loss and the defrosting heating loss to the total nominal heating capacity of the unit in the single defrosting circulation process of the air source heat pump.
3. The method of modeling a predicted optimal defrost control point for an air source heat pump as recited in claim 2 wherein Q isL1-nominal frost loss (kJ); qL2-nominal defrost loss (kJ); t is ti-a frosting run time or defrosting control point(s); t is tn-defrost end time(s); q. q.shc-nominal heating capacity (kW); q. q.shc2-actual heat production (kW);
nominal heating loss coefficientNLThe calculation is as follows:
nominal frost loss:
Figure FDA0002504199130000011
nominal defrost loss:
Figure FDA0002504199130000012
nominal heating loss coefficient:
Figure FDA0002504199130000013
。
4. the method for building a model for predicting the optimal defrosting control point of an air source heat pump according to claim 1, wherein in the step (2), the GRNN model is built by training the operation data of the air source heat pump unit in the perennial heating season, and the relative error of the simulation data is within ± 10%.
5. The method for establishing the model for predicting the optimal defrosting control point of the air source heat pump according to the claim 1, wherein in the step (3), the optimal defrosting control point database comprises the optimal defrosting control points of the air source heat pump under the working conditions that the ambient temperature is-15 to 6 ℃ and the relative humidity is 50 to 100%, the temperature interval is 1 ℃ and the humidity interval is 1%.
6. The method for building a model for predicting the optimal defrosting control point of an air source heat pump according to claim 1, wherein in the step (4), the built optimal defrosting control point prediction model only inputs the frosting condition parameters, namely the ambient temperature and the ambient humidity, so as to output the optimal defrosting control point of the air source heat pump under the condition.
7. A model for predicting an optimal defrost control point for an air-source heat pump prepared according to the method of any of claims 1 to 6.
CN202010445957.2A 2020-05-22 2020-05-22 Model for predicting optimal defrosting control point of air source heat pump and establishing method thereof Pending CN111678279A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010445957.2A CN111678279A (en) 2020-05-22 2020-05-22 Model for predicting optimal defrosting control point of air source heat pump and establishing method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010445957.2A CN111678279A (en) 2020-05-22 2020-05-22 Model for predicting optimal defrosting control point of air source heat pump and establishing method thereof

Publications (1)

Publication Number Publication Date
CN111678279A true CN111678279A (en) 2020-09-18

Family

ID=72453634

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010445957.2A Pending CN111678279A (en) 2020-05-22 2020-05-22 Model for predicting optimal defrosting control point of air source heat pump and establishing method thereof

Country Status (1)

Country Link
CN (1) CN111678279A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112413948A (en) * 2020-11-18 2021-02-26 北京工业大学 Laboratory measurement system and method for defrosting control point of air source heat pump

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2006110165A2 (en) * 2004-09-22 2006-10-19 Northrop Grumman Corporation Process for refrigerant charge level detection using a neural net
CN105716340A (en) * 2016-03-09 2016-06-29 北京工业大学 Multi-zone frosting map-based defrosting control method of air source heat pump
CN107289693A (en) * 2017-07-11 2017-10-24 上海理工大学 A kind of Defrost method
CN111156657A (en) * 2019-12-25 2020-05-15 珠海格力电器股份有限公司 Air conditioner frosting state determining method and device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2006110165A2 (en) * 2004-09-22 2006-10-19 Northrop Grumman Corporation Process for refrigerant charge level detection using a neural net
CN105716340A (en) * 2016-03-09 2016-06-29 北京工业大学 Multi-zone frosting map-based defrosting control method of air source heat pump
CN107289693A (en) * 2017-07-11 2017-10-24 上海理工大学 A kind of Defrost method
CN111156657A (en) * 2019-12-25 2020-05-15 珠海格力电器股份有限公司 Air conditioner frosting state determining method and device

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
吴旭等: "最佳除霜控制点计算模型的建立", 《2017年全国热泵学术年会论文集》 *
王伟等: "空气源热泵名义制热量损失系数模型研究", 《制冷学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112413948A (en) * 2020-11-18 2021-02-26 北京工业大学 Laboratory measurement system and method for defrosting control point of air source heat pump
CN112413948B (en) * 2020-11-18 2021-11-19 北京工业大学 Laboratory measurement system and method for defrosting control point of air source heat pump

Similar Documents

Publication Publication Date Title
CN109376960A (en) Load Forecasting based on LSTM neural network
CN110046743A (en) Energy Consumption of Public Buildings prediction technique and system based on GA-ANN
CN107909220A (en) Electric heating load prediction method
CN109084415A (en) Central air-conditioning operating parameter optimization method based on artificial neural network and genetic algorithms
CN108399470B (en) Indoor PM2.5 prediction method based on multi-example genetic neural network
CN103912966A (en) Optimal control method for ground source heat pump refrigerating system
CN104484715A (en) Neural network and particle swarm optimization algorithm-based building energy consumption predicting method
CN107644297B (en) Energy-saving calculation and verification method for motor system
CN110701796B (en) Energy-saving control system of hot water system based on cloud prediction algorithm
CN112733443B (en) Water supply network model parameter optimization checking method based on virtual monitoring points
CN104865827B (en) A kind of pumping production optimization method based on multi-state model
CN112712189A (en) Heat supply demand load prediction method
CN108038568A (en) A kind of changeable weight combination Short-Term Load Forecasting of Electric Power System based on particle cluster algorithm
CN106650125A (en) Method and system for optimizing centrifugal compressor impeller
CN112884012A (en) Building energy consumption prediction method based on support vector machine principle
CN112418495A (en) Building energy consumption prediction method based on longicorn stigma optimization algorithm and neural network
CN114936742A (en) Water supply system scheduling agent decision method
CN111678279A (en) Model for predicting optimal defrosting control point of air source heat pump and establishing method thereof
CN108376294A (en) A kind of heat load prediction method of energy supply feedback and meteorologic factor
CN113111419A (en) Method and system for establishing and predicting air-conditioning load prediction model in office building
CN113757781A (en) Heat supply load prediction energy-saving control method and system based on BP neural network prediction model
CN111582588A (en) Building energy consumption prediction method based on triple convolution fusion GRU
CN113959071B (en) Centralized water chilling unit air conditioning system operation control optimization method based on machine learning assistance
Chen et al. Research on energy-saving optimization model based on building energy consumption data
CN115839776A (en) Heat radiation error correction method for bolt and nut gasket structure

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20200918