CN112541259A - Self-feedback temperature adjusting method and system for independent heating system - Google Patents
Self-feedback temperature adjusting method and system for independent heating system Download PDFInfo
- Publication number
- CN112541259A CN112541259A CN202011424106.6A CN202011424106A CN112541259A CN 112541259 A CN112541259 A CN 112541259A CN 202011424106 A CN202011424106 A CN 202011424106A CN 112541259 A CN112541259 A CN 112541259A
- Authority
- CN
- China
- Prior art keywords
- heat
- self
- feedback
- temperature
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
Abstract
The self-feedback temperature regulating method and system for independent heat supply system includes the steps of forming the heat supply period with preheating stage, temperature raising stage, temperature regulating stage and heat insulating stage; and parameters given by the input parameter refinement table are added properly, parameters influencing a prediction result are added, a mathematical model of each heat consumption and heat production parameter is established, and then a mathematical model for predicting the hourly heat demand is established. A set of self-feedback temperature regulating system is introduced in the temperature regulating stage and used for regulating the hourly heat load, so that the hourly heat demand is quickly controlled to approach the actual heat demand; meanwhile, the neural network model is used for calculating the heat load time by time, so that the system can well cope with the conditions of holidays, sudden changes of work and rest rules and the like.
Description
Technical Field
The disclosure relates to the technical field of building heating and control, in particular to a self-feedback temperature adjusting method and system for an independent heating system.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
At present, a heating system in China basically has no automatic control device at a tail end hot user position, so that the cold and heat distribution is uneven, and the phenomena that some users wear short sleeves and window opening indoors, some users wear cotton clothes indoors and the like occur. The condition is not only poor in comfort level and satisfaction degree of users, but also not beneficial to body health of the users, and waste of heating energy is caused; therefore, the accuracy of heat load prediction directly influences the comfort level of a resident in the heating season, and accurate prediction of the heat supply quantity is very necessary; researchers in this field both domestically and abroad have done a lot of research work for many years, and have proposed many aspects and prediction schemes.
In some domestic researches, white snow, light and the like analyze and research the functions and types of urban complexes at home and abroad, change rules of factors such as equipment, lamp use, personnel activities and the like in resident rooms are analyzed through investigation and research, simulation is carried out on indoor scenes by using a computer, a model is built on the basis of the simulation, and heat load is predicted; li Qi et al think that the influence proportion of outdoor temperature to heat load is great, firstly put forward a set of improved BRP neural network's rolling prediction model, then put forward a set of dynamic K mean value clustering neural network prediction model based on genetic algorithm again. The later establishes a model by using a BP neural network, firstly analyzes the characteristics of outdoor temperature and date, quantifies the characteristics, and then carries out heat demand to obtain the hourly heat load of the future day, and the prediction is more accurate by using the method; baishan et al conducted intensive studies on outdoor weather changes as the main basis to establish a thermal load calculation model. The method is based on a large amount of actual meteorological data and carries out linear fitting on the heat load. The model has higher prediction accuracy rate under the condition of ensuring that the error of engineering application is met; the Yanfan and other people use a certain industrial park in China as a research object, firstly carry out on-site investigation, then respectively obtain maximum, minimum and average heat loads by using a coefficient method and a typical daily load superposition method, and finally determine a heat load change rule.
In foreign research, when carrying out thermal load prediction, Peder Bacher et al mainly adopt a time series method to establish a model and take an independent room as a research object for research. But the result is not ideal, uncertain weather conditions and indoor personnel activities have great influence on the prediction of heat demand, especially solar radiation; willian J Stevenson used neural networks to initially build heat demand prediction models. Time variation and various outdoor meteorological conditions are considered.
In summary, the inventor finds that although certain results are obtained at home and abroad in the research of heat supply and heat load prediction, the inventor finds that each system in the prior art has some defects, and the heat demand prediction value and the actual heat load still have large errors; although each influence factor is considered as weekly as possible during calculation, each researcher predicts the heat load based on historical data, but the historical data cannot replace the actual weather condition changing every year, and is even applicable to buildings in different geographical positions.
Disclosure of Invention
In order to solve the problems, the invention provides a self-feedback temperature regulation method and a self-feedback temperature regulation system for an independent heating system, and the scheme fully considers various outdoor and indoor influence factors through a time-by-time heat load calculation model, and considers the work and rest conditions of personnel and the holiday and festival scores of working days, so as to establish a mathematical model for heat demand prediction; by the self-feedback temperature regulating system, effective data are obtained while the predicted heat demand is close to the actual heat load; and the entity data of the building main body is used for training the neural network, so that a stable and efficient heat demand predicted value is obtained.
According to a first aspect of embodiments of the present disclosure, there is provided a self-feedback attemperation method for a standalone heating system, comprising:
dividing the heat supply process of a target building into preheating, heating, self-feedback regulation and heat preservation stages in advance;
constructing a time-by-time heat load calculation model of the building based on the environment of the target building;
calculating the hourly heat demand by using the hourly heat load calculation model and outputting the hourly heat demand;
and in the self-feedback adjusting stage, dynamically adjusting the coefficient of the time-by-time heat load calculation model according to the temperature difference between the set temperature and the actual temperature, and outputting heat until the daily heat supply of the target building is completed.
Furthermore, the construction of the time-by-time heat load calculation model fully considers various indoor and outdoor influence factors, including the heat consumption of external wall temperature difference heat transfer, the heat consumption of external window temperature difference heat transfer, irradiance additional heat load, lamp heat dissipation cold load, human body sensible heat dissipation cold load, wind power additional heat load, cold wind invasion additional heat load, cold wind permeation heat consumption, adjacent internal wall temperature difference heat transfer heat consumption, adjacent corridor surface temperature difference heat transfer heat consumption and ground heat consumption.
Further, in the self-feedback temperature adjustment stage, the coefficient of the time-by-time thermal load calculation model is dynamically adjusted according to the temperature difference between the set temperature and the actual temperature, and the method comprises the following steps:
comparing the temperature difference between the indoor actual temperature and the set temperature, and if the actual temperature is higher than the set temperature by 0.5 ℃, reducing the coefficient of the heat load calculation model; if the actual temperature is lower than the set temperature, the coefficient of the heat load calculation model remains unchanged.
According to a second aspect of the embodiments of the present disclosure, there is provided another self-feedback temperature adjustment method for a standalone heating system, which constructs a training set using the time-by-time heat demand at a specific time outputted by the self-feedback temperature adjustment method for the standalone heating system, the method including:
dividing the heat supply process of a target building into preheating, heating, self-feedback regulation and heat preservation stages in advance; training a neural network model by adopting the training set;
the product of the hourly heat demand and the regulating coefficient output by the pre-trained neural network model is used as the actual hourly heat demand and is output;
in the self-feedback adjusting stage, the adjusting coefficient is dynamically adjusted according to the temperature difference between the set temperature and the actual temperature, and heat output is carried out until daily heat supply of the target building is completed;
and the training set is expanded by utilizing the time-by-time output result of the neural network model, and the neural network model is retrained by utilizing the expanded training set at a specific moment.
Furthermore, the construction of the time-by-time heat load calculation model fully considers various indoor and outdoor influence factors, including the heat consumption of external wall temperature difference heat transfer, the heat consumption of external window temperature difference heat transfer, irradiance additional heat load, lamp heat dissipation cold load, human body sensible heat dissipation cold load, wind power additional heat load, cold wind invasion additional heat load, cold wind permeation heat consumption, adjacent internal wall temperature difference heat transfer heat consumption, adjacent corridor surface temperature difference heat transfer heat consumption and ground heat consumption.
Further, in the self-feedback temperature adjustment stage, the coefficient of the time-by-time thermal load calculation model is dynamically adjusted according to the temperature difference between the set temperature and the actual temperature, and the method comprises the following steps:
comparing the temperature difference between the indoor actual temperature and the set temperature, and if the actual temperature is higher than the set temperature by 0.5 ℃, reducing the coefficient of the heat load calculation model; if the actual temperature is lower than the set temperature, the coefficient of the heat load calculation model remains unchanged.
Further, the extension of the training set comprises: in the self-feedback regulation stage, when the regulation parameters are selected to be kept unchanged and preset specific time is met, data including the time-by-time heat demand at the time are added into a training set for retraining the neural network model.
According to a third aspect of embodiments of the present disclosure, there is provided a self-feedback tempering system for a self-contained heating system, which utilizes the self-feedback tempering method for a self-contained heating system described above.
According to a fourth aspect of embodiments of the present disclosure, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory for execution, the processor when executing the program implementing the self-feedback attemperation method for a standalone heating system.
According to a fifth aspect of embodiments of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a self-feedback attemperation method for a standalone heating system as described.
Compared with the prior art, the beneficial effect of this disclosure is:
(1) the invention provides a hourly heat demand forecasting model applied to an independent heating system, which fully considers various outdoor and indoor influence factors and also considers the work and rest conditions of personnel and the holiday and festival scores of working days so as to establish a mathematical model for forecasting the heat demand. Through the self-feedback temperature regulating system in the disclosure, effective data is obtained while the predicted heat demand is ensured to be close to the actual heat load. And training a neural network by using the entity data of the building main body so as to obtain a stable and efficient heat demand predicted value.
(2) The scheme of the disclosure establishes a complete system which not only comprehensively considers the conditions of buildings, weather, heat supply standards, working and rest rules of personnel and the like, but also can predict the hourly heat load in the heat supply period so as to achieve the purpose of reducing energy consumption; under the premise of ensuring the conditions, the system can well cope with the conditions of holidays, sudden change of work and rest rules and the like by utilizing the neural network model to calculate the heat load time by time.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
FIG. 1 is a floor plan and a room number diagram according to a first embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a heating process stage according to a first embodiment of the disclosure;
FIG. 3 is a schematic structural diagram of a self-feedback attemperation system according to a first embodiment of the disclosure;
fig. 4 is a schematic structural diagram of a holiday hourly heat demand prediction system according to a first embodiment of the disclosure.
Detailed Description
The present disclosure is further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The first embodiment is as follows:
the object of the present embodiment is a self-feedback tempering method for a stand-alone heating system.
A self-feedback attemperation method for a standalone heating system, comprising:
dividing the heat supply process of a target building into preheating, heating, self-feedback regulation and heat preservation stages in advance;
constructing a time-by-time heat load calculation model of the building based on the environment of the target building;
calculating the hourly heat demand by using the hourly heat load calculation model and outputting the hourly heat demand;
and in the self-feedback adjusting stage, dynamically adjusting the coefficient of the time-by-time heat load calculation model according to the temperature difference between the set temperature and the actual temperature, and outputting heat until the daily heat supply of the target building is completed.
Specifically, taking a practical case of a certain heating company as an example, the method described in this embodiment is described in detail, and the apartment conditions are as follows:
-total project building area 22356 square meters;
-the building body is divided into a first underground layer, 12 above ground layers and 48.9 meters high;
the company is responsible for providing a heating system solution for rooms of 5-12 floors, up to 14904 square meters and 240 rooms.
In order to solve the problem of economic and comfortable heat supply, the hourly heat load of the heating period of the apartment needs to be predicted so as to guide the operation scheduling of the heating equipment, and the heat demand prediction model of the invention is used for prediction.
The floor plan is shown in figure 1.
Preparation work before establishing heat demand model
1. The average temperature in the room is used as the actual temperature.
(1) Measurement of average temperature: before formal heating of apartment, five accurate thermometers are placed at four corners and middle position in house, and the measured temperature constitutes the average temperature T of apartmentmean。
Tmean＝(Tt1+Tt2+Tt3+Tt4+Tt5+TMaster and slave)/6
T main: domestic temp. measurer
(2) Will obtain TmeanThe actual measured temperature T of the temperature measurerMaster and slavePaired one to one, i.e. for calculating the room temperature T during the actual heatingi,jTemperature T measured by main temperature measurerMaster and slavePaired Tmean。
2. Assuming a heating temperature range: t isa～Tb
3. Assume that apartment people have two dwelling hours, noon and evening:
[0,ta(i,j)]∪[tb(i,j),tc(i,j)]∪[td(i,j),1439]min
i-5, …,12 is floor number
ta, tb, tc, td: the time of day is divided into three phases, and four endpoints of ta, tb, tc, and td are set.
4. Assuming a heating period:
tworker's tool：[0,ta(i,j)]∪[tb(i,j)-X,tc(i,j)]∪[td(i,j)-X,1439]min
X is delay time, namely the time for heating the apartment in advance, and X can be taken as 20 min.
This patent decomposes twice heat supply process into four stages respectively.
Stage one: the preheating stage T is set to
The time period is as follows:
[tb(i,j)-X,tb(i,j)]∪[td(i,j)-X,td(i,j)]min
heating temperature range: t isa～Tb
And a second stage: the temperature raising period T was set to 0.618 × (T)b+Ta) The time period is as follows:
[tb(i,j),tb(i,j)+X]∪[td(i,j),td(i,j)+X]min
and a third stage: temperature adjusting stage of self-feedback system:
[0,ta(i,j)-X]∪[tb(i,j)+X,tc(i,j)-X]∪[td(i,j)+X,1439]min
and a fourth stage: the heat-preservation period T is set as
The time period is as follows:
[ta(i,j)-X,ta(i,j)]∪[tc(i,j)-X,tc(i,j)]min
the hourly heat demand Q can be obtained according to the T set in different stagesi,j(t); the time-by-time heat demand of each moment of the four stages is superposed to obtain the day-by-day heat demand Qi,j。
(II) establishing a time-by-time heat demand model of the room (i, j)
γ: self-feedback temperature regulating coefficient with initial value of 1
Q1: external wall temperature difference heat transfer and heat consumption
Q2: external window temperature difference heat transfer and heat consumption
Q3: irradiance added heat load
Q4: lamp heat dissipation cold load
Q5: human body sensible heat radiation cold load
Q6: wind power additional heat load
Q7: additional heat load for cold air invasion
Q8: heat consumption by cold air infiltration
Q9: heat consumption of adjacent inner wall by temperature difference heat transfer
Q10: heat consumption by temp. difference between adjacent gallery surfaces
Q11: heat consumption of ground
i: floor number
j: room number
t: time of day
The heat consumption and heat production parameters are specifically calculated as follows:
(1) outer wall temperature difference heat transfer and heat consumption quantity Q1
Q1＝K1×F1×(T-TOuter cover)......i≠12,j≠1,15,16,30
K1: outer wall heat transfer coefficient w/m2 DEG C
F1: the area of the outer wall on the north and south sides is m 2;
Ti,j: actual indoor temperature
Note: when i is 12, the external wall area is added to the external wall area of the roof.
Q1＝K1×(F1+F7)×(Ti,j-TOuter cover)
F7: area of roof
When j is 1,15,16,30, the external wall area is added with the external wall area of east-west side
Q1＝K1×(F1+F3)×(Ti,j-TOuter cover)
F3: east-west side outer wall and adjacent roof area
(2) External window temperature difference heat transfer and heat consumption quantity Q2
Q2＝K2×F2×(Ti,j-TOuter cover)×α
K2: outer window heat transfer coefficient w/m2 DEG C
F2: outer window area m 2;
α: window frame correction factor, see "practical Heat supply and air Conditioning design Manual
(3) Irradiance with additional thermal load Q3
The solar irradiance is used for carrying out real-time calculation on the addition of the heat load to obtain the irradiance-added heat load Q of the building3。
Q3＝Q3 1+Q3 2
Q3 1: irradiance induced exterior window thermal load
Q3 1＝F2×Xd1×Xg1×J
Xd1: outer window correction factor
Xg1: external window solar radiation absorptivity
J: solar irradiance.w/m 2; the solar irradiance of the patent is given for a time interval of 60s, and the irradiance given last time is taken as the irradiance at each moment. Because the irradiance of east, south, west, north and horizontal planes of the building are different, J takes different values J on different external wall surfacesEast，JWestern medicine，JSouth China，JNorth China，JHorizontal plane
Q3 2: irradiance induced thermal loading of exterior walls
Q3 2＝F1×Xd2×Xg2×J......i≠12；j≠1,15,16,30
Xd2: coefficient of correction for exterior wall
Xg2: external wall solar radiation absorptivity
Note:
when i is 12, the outer wall area is added with the outer wall of the roof, and the irradiance of the outer wall of the roof is the horizontal plane irradiance
Q3 2＝(F1×J+F7×JHorizontal plane)×Xd2×Xg2
When j is 1,30, the area of the outer wall comprises a west outer wall, and the irradiance of the west outer wall is west irradiance
Q3 2＝(F1×J+F3×JWestern medicine)×Xd2×Xg2
When j is 15 and 16, the area of the outer wall comprises an east outer wall, and the irradiance of the east outer wall is the east irradiance
Q3 2＝(F1×J+F3×JEast)×Xd2×Xg2
(4) Lamp heat dissipation cold load Q4
In northern winter, the evening time is generally reached at about six points, and if apartment workers turn on the lamp at 18 points and turn off the lamp at 23 points in a unified manner, a piecewise function of the heat dissipation and cold load of the lamp is obtained.
M: power w required by lighting lamp
n1: the ballast consumes power coefficient, n1＝1.0
n2: the heat insulation coefficient of the lampshade is that when the upper part of the fluorescent lampshade is provided with a small hole (the lower part is a glass plate) and the fluorescent lampshade can utilize natural ventilation to dissipate heat in a ceiling, n is taken20.5-0.6; non-ventilation hole n of fluorescent lamp shade2＝0.6～0.8
Cdj: cold load coefficient of illumination and heat dissipation
Selecting n according to' design Specification for heating, ventilating and air conditioning1＝1.0，n2＝0.6，Cdj＝0.37
(5) Human body sensible heat radiation cold load Q5
Q5＝q×n×φ×Crt
q: sensible heat dissipation capacity w of adult men with different room temperatures and labor properties
n: total number of people in house
Phi: cluster coefficient
Crt: coefficient of human body sensible heat and heat dissipation and cold load
Referring to the design code of heating ventilation and air conditioning, q is 83, phi is 0.93 and C is selectedrt＝0.84
(6) High additional thermal load: when the room clear height of the civil buildings and the auxiliary buildings of the industrial enterprises exceeds 4m, the addition rate is 2% and the maximum addition rate does not exceed 15% every 1 m.
The net height of the heating floor of the company does not exceed 4m, and the additional heat load is not considered.
(7) Wind power additional heat load Q6
Q6＝βfl(i)×Q1
βfl(i) The method comprises the following steps Wind add-on ratio of i-th layer
In buildings on highlands, rivers, coasts and open fields without wind sheltering, and buildings with particularly high heights in cities, towns and plant areas, the heat load of the vertical external enclosure structure is added by 5-10%. Order to
The 5 th floor takes the wind power addition rate of 5%, the 12 th floor takes the wind power addition rate of 10%, and the middle floors take the wind power addition rates in a proportional relation.
(8) Additional heat load Q for cold air invasion7
Under the action of wind pressure and hot pressing in winter, cold air can invade through the opened outer door, can cause the loss of indoor heat, use the cold wind invasion heat consumption computational formula in the traditional heat load computational method.
Q7＝Q10 1×N
Q10 1: external door temperature difference heat transfer and heat consumption
(9) Heat consumption by cold air infiltration Q8
The cold air from outdoor can enter the room through the door and window seams, and the process of heating the infiltrated cold air can result in the loss of heat in the room. The heat loss caused by the infiltration of the cold air from the outside into the room through the gap is the heat consumption of the cold air infiltration.
Q8＝0.278×Cp×Vlf×ρw×(Ti,j-TOuter cover)
0.278 is a unit conversion coefficient 1kj/h ═ 0.278w
Cp: the constant pressure specific heat capacity is j/kg DEG C; get Cp＝1j/kg·℃
Vlf: volume of cold air m 3;
ρw: density of cold air kg/m 3;
Vlf＝L×l×n3
l: penetration per unit length m3/m
l: gap length m
n3: number of penetrations (number of room air changes less than 500m3 is set to 0.7/h)
(10) Heat consumption Q for temperature difference heat transfer of adjacent inner walls9
When the adjacent room is not in a heat supply state, the temperature difference between the room and the adjacent room is observed, so that the temperature difference of the inner wall of the adjacent room is formed for heat transfer and heat consumption
Q9＝K3F3×[(Ti,j-Ti,j-1)+(Ti,j-Ti,j+1)]......j＝2,3,...,14
K3: interproximal roof heat transfer parameter w/m2 DEG C
Note: the room in east mountain and west mountain has only one side with inner wall adjacent to the room and the other side adjacent to the outside to generate heat exchange, so that
When j is 1,30,
Q9＝K3F3×(Ti,j-Ti,j+1)
when j is 15,16,
Q9＝K3F3×(Ti,j-Ti,j-1)
(11) heat consumption Q of adjacent corridor surface by temperature difference heat transfer10
The heat consumption of the temperature difference of the adjacent gallery surfaces comprises the heat consumption of the outer door and the wall surfaces.
Q10＝Q10 1+Q10 2
Q101: external door temperature difference heat transfer and heat consumption
Q10 1＝K4×F4×(Ti,j-TCorridor)
TCorridor: temperature of corridor
K4: the heat transfer coefficient of the outer door is w/m2 DEG C
F4: outer door area m2
Q10 2: heat transfer and consumption of adjacent gallery wall
Q10 2＝K3×F5×(Ti,j-TCorridor)
F5: adjacent corridor roofing area m2
(12) Ground heat consumption Q11
Q11＝K5(F6+F7)×[(Ti,j-Ti-1,j)+(Ti,j-Ti+1,j)]......i＝5,6,...,11
K5: ground heat transfer coefficient w/m2 DEG C
F6: area of lower floor m2
Note: the ground heat consumption of the top layer is generated only by the lower ground, the heat consumption of the upper ground is the heat exchange with the outside, so when i is 12,
Q11＝KjdFjd×(Ti,j-Ti-1,j)
(III) self-feedback temperature regulating system
tInverse direction＝[0,ta(i,j)-X]∪[tb(i,j)+X,tc(i,j)-X]∪[td(i,j)+X,1439]min
The self-feedback temperature regulating system is explained in detail (the flow chart of the self-feedback temperature regulating system is shown in a figure 3):
the first step is as follows: inputting gamma to be 1 and t to be 0, and starting the system;
the second step is that: calculating the time-by-time heat demand according to the gamma and the t and outputting the calculated time-by-time heat demand;
the third step: the temperature difference between the indoor actual temperature and the set temperature is judged, the judgment is carried out according to the set error threshold value, and gamma is adjusted (the threshold value is automatically adjusted according to the needs of enterprises, and +/-0.5 ℃ is selected as an example in the patent). If the actual temperature is 0.5 ℃ higher than the set temperature, the coefficient gamma is reduced by 0.01 (the regulation amplitude of gamma can be adjusted according to the actual condition); if the actual temperature is lower than the set temperature by 0.5 ℃, the coefficient gamma is increased by 0.01; if the temperature difference between the actual temperature and the set temperature is lower than 0.5 ℃, keeping the gamma unchanged;
the fourth step: selecting gamma which is kept unchanged, namely the temperature difference between the actual temperature and the set temperature is within an acceptable range and meets the requirement that t is within (0 minute, 10 minutes, 20 minutes, 30 minutes, 40 minutes and 50 minutes) of a specific moment, and exporting data such as hourly heat demand and the like of the moment to a folder for training a neural network;
the fifth step: updating the time t to t + 1;
and a sixth step: if t belongs to the t inverse, returning to the second step for circulation, and if t does not belong to the t inverse, entering the next process;
the seventh step: and (6) judging whether t is less than 1440 min. And if t is greater than or equal to 1440min, ending the circulation, namely ending the adjustment of the self-feedback temperature adjusting stage on the same day. And if t is less than 1440min, returning to the sixth step.
Example two:
it is an object of the present embodiment to provide another self-feedback tempering method for a stand-alone heating system.
A self-feedback attemperation method for a standalone heating system, comprising:
the time-by-time heat demand at a specific moment output by the self-feedback temperature regulation method for the independent heating system is utilized to construct a training set, and the method comprises the following steps:
dividing the heat supply process of a target building into preheating, heating, self-feedback regulation and heat preservation stages in advance; training a neural network model by adopting the training set;
the product of the hourly heat demand and the regulating coefficient output by the pre-trained neural network model is used as the actual hourly heat demand and is output;
in the self-feedback adjusting stage, the adjusting coefficient is dynamically adjusted according to the temperature difference between the set temperature and the actual temperature, and heat output is carried out until daily heat supply of the target building is completed;
and the training set is expanded by utilizing the time-by-time output result of the neural network model, and the neural network model is retrained by utilizing the expanded training set at a specific moment.
The dynamic model of the heat supply process is very complex, the heat transmission process cannot be described with an ideal equation and fixed parameters at high precision, the heat supply network is a large hysteresis system, heat loads input by time can enter from an input port, the heat loads and the whole apartment are subjected to temperature exchange through air flow exchange and air heat transfer, and the control effect can be exerted after a period of time.
In order to better predict the heat demand of the whole heating season, a model for predicting the time-by-time heat demand based on a neural network is established and is specially used for the situations of holidays or temporary rest.
In the self-feedback temperature adjusting stage, real-time data within 0.5 ℃ of the difference between the indoor actual temperature and the set temperature is selected, the indoor actual temperature Ti, j, the set temperature, the hourly heat demand after temperature adjustment and the outdoor temperature at specific time (0 minute, 10 minutes, 20 minutes, 30 minutes, 40 minutes and 50 minutes) given by the feedback temperature adjusting system are taken as input neurons, and the hourly heat demand after temperature adjustment at the next time is taken as output neurons. Each set of data is a training sample.
Feeding all training samples obtained on the first day into a neural network; the activation function uses a sigmoid activation function, and the learning rate is set to be 0.1; input neurons 4: indoor actual temperature, set temperature, hourly heat demand after temperature regulation and outdoor temperature; the number of the hidden layers is temporarily set to be 5; and 1 output neuron is the hourly heat demand of the next sample after temperature regulation.
Because many new training samples are generated each day, retraining the neural network every time a sample is added can be too complex, so at zero point each day, the neural network is retrained using the samples in the folder used for neural network training.
The method comprises the following steps:
the first step is as follows: inputting gamma to be 1 and t to be 0, and starting the system;
the second step is that: inputting a variable value of a last moment required by an input neuron;
the third step: calculating the hourly heat demand according to a model trained by the neural network, and outputting the product of the coefficient gamma and the hourly heat demand calculated by the neural network as the actual hourly heat demand;
the fourth step: the temperature difference between the indoor actual temperature and the set temperature is judged, the judgment is carried out according to the set error threshold value, and gamma is adjusted (the threshold value is automatically adjusted according to the needs of enterprises, and +/-0.5 ℃ is selected as an example in the patent). If the actual temperature is 0.5 ℃ higher than the set temperature, the coefficient gamma is reduced by 0.01 (the regulation amplitude of gamma can be adjusted according to the actual condition); if the actual temperature is lower than the set temperature by 0.5 ℃, the coefficient gamma is increased by 0.01; if the temperature difference between the actual temperature and the set temperature is lower than 0.5 ℃, keeping the gamma unchanged;
the fifth step: selecting gamma which is kept unchanged, namely the temperature difference between the actual temperature and the set temperature is within an acceptable range and meets the requirement that t is within (0 minute, 10 minutes, 20 minutes, 30 minutes, 40 minutes and 50 minutes) of a specific moment, and exporting data such as hourly heat demand and the like of the moment to a folder for training a neural network;
and a sixth step: updating the time t to t + 1;
the seventh step: and (6) judging whether t is less than 1440 min. And if t is greater than or equal to 1440min, ending the circulation, namely ending the adjustment of the self-feedback temperature adjusting stage on the same day. If t is less than 1440min, returning to the second step.
Example three:
it is an object of the present embodiment to provide a self-feedback tempering system for an independent heating system.
A self-feedback temperature adjusting system for an independent heating system utilizes the self-feedback temperature adjusting method for the independent heating system.
Example four:
the embodiment aims at providing an electronic device.
An electronic device comprising a memory, a processor and a computer program stored for execution on the memory, wherein the processor when executing the program implements a self-feedback attemperation method for a standalone heating system as described above.
Example five:
it is an object of the present embodiments to provide a non-transitory computer-readable storage medium.
A non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a self-feedback attemperation method for a standalone heating system as described above.
The self-feedback temperature adjusting method and the system for the independent heating system can be completely realized, and have wide application prospect.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Although the present disclosure has been described with reference to specific embodiments, it should be understood that the scope of the present disclosure is not limited thereto, and those skilled in the art will appreciate that various modifications and changes can be made without departing from the spirit and scope of the present disclosure.
Claims (10)
1. A self-feedback attemperation method for a self-contained heating system, comprising:
dividing the heat supply process of a target building into preheating, heating, self-feedback regulation and heat preservation stages in advance;
constructing a time-by-time heat load calculation model of the building based on the environment of the target building;
calculating the hourly heat demand by using the hourly heat load calculation model and outputting the hourly heat demand;
and in the self-feedback adjusting stage, dynamically adjusting the coefficient of the time-by-time heat load calculation model according to the temperature difference between the set temperature and the actual temperature, and outputting heat until the daily heat supply of the target building is completed.
2. The self-feedback temperature adjustment method for the independent heating system as claimed in claim 1, wherein the time-by-time heat load calculation model is constructed by fully considering various indoor and outdoor influence factors, including external wall temperature difference heat transfer and heat consumption, external window temperature difference heat transfer and heat consumption, irradiance additional heat load, lamp heat dissipation cold load, human body sensible heat dissipation cold load, wind force additional heat load, cold wind invasion additional heat load, cold wind penetration heat consumption, adjacent internal wall temperature difference heat transfer and heat consumption, adjacent corridor surface temperature difference heat transfer and heat consumption, and ground heat consumption.
3. A self-feedback tempering method for a free-standing heating system according to claim 1, wherein said self-feedback tempering phase dynamically adjusts coefficients of said time-wise thermal load calculation model according to a temperature difference between a set temperature and an actual temperature, comprising the steps of:
comparing the temperature difference between the indoor actual temperature and the set temperature, and if the actual temperature is higher than the set temperature by 0.5 ℃, reducing the coefficient of the heat load calculation model; if the actual temperature is lower than the set temperature, the coefficient of the heat load calculation model remains unchanged.
4. A self-feedback tempering method for a self-contained heating system, characterized in that a training set is constructed using the time-by-time heat demand at a specific time outputted by a self-feedback tempering method for a self-contained heating system according to any one of claims 1 to 3, the method comprising:
dividing the heat supply process of a target building into preheating, heating, self-feedback regulation and heat preservation stages in advance; training a neural network model by adopting the training set;
the product of the hourly heat demand and the regulating coefficient output by the pre-trained neural network model is used as the actual hourly heat demand and is output;
in the self-feedback adjusting stage, the adjusting coefficient is dynamically adjusted according to the temperature difference between the set temperature and the actual temperature, and heat output is carried out until daily heat supply of the target building is completed;
and the training set is expanded by utilizing the time-by-time output result of the neural network model, and the neural network model is retrained by utilizing the expanded training set at a specific moment.
5. The self-feedback temperature adjustment method for the independent heating system, as claimed in claim 4, wherein the time-by-time heat load calculation model is constructed by fully considering various indoor and outdoor influence factors, including external wall temperature difference heat transfer and heat consumption, external window temperature difference heat transfer and heat consumption, irradiance additional heat load, lamp heat dissipation cold load, human body sensible heat dissipation cold load, wind power additional heat load, cold wind invasion additional heat load, cold wind penetration heat consumption, adjacent internal wall temperature difference heat transfer and heat consumption, adjacent corridor surface temperature difference heat transfer and heat consumption, and ground heat consumption.
6. A self-feedback tempering method for a free-standing heating system according to claim 4, wherein said self-feedback tempering phase dynamically adjusts coefficients of said time-wise thermal load calculation model according to a temperature difference between a set temperature and an actual temperature, comprising the steps of:
comparing the temperature difference between the indoor actual temperature and the set temperature, and if the actual temperature is higher than the set temperature by 0.5 ℃, reducing the coefficient of the heat load calculation model; if the actual temperature is lower than the set temperature, the coefficient of the heat load calculation model remains unchanged.
7. A self-feedback tempering method for a free-standing heating system according to claim 4, wherein said extension of said training set comprises: in the self-feedback regulation stage, when the regulation parameters are selected to be kept unchanged and preset specific time is met, data including the time-by-time heat demand at the time are added into a training set for retraining the neural network model.
8. A self-feedback tempering system for a free-standing heating system, characterized in that said system utilizes a self-feedback tempering method for a free-standing heating system according to any of claims 1-7.
9. An electronic device comprising a memory, a processor and a computer program stored for execution on the memory, the processor when executing the program implementing a self-feedback tempering method for a free-standing heating system according to any of claims 1-7.
10. A non-transitory computer readable storage medium having stored thereon a computer program, characterized in that the program, when executed by a processor, implements a self-feedback tempering method for a standalone heating system, as claimed in any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011424106.6A CN112541259B (en) | 2020-12-08 | 2020-12-08 | Self-feedback temperature adjusting method and system for independent heating system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011424106.6A CN112541259B (en) | 2020-12-08 | 2020-12-08 | Self-feedback temperature adjusting method and system for independent heating system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112541259A true CN112541259A (en) | 2021-03-23 |
| CN112541259B CN112541259B (en) | 2022-07-08 |
Family
ID=75019547
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011424106.6A Active CN112541259B (en) | 2020-12-08 | 2020-12-08 | Self-feedback temperature adjusting method and system for independent heating system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112541259B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114516403A (en) * | 2022-03-07 | 2022-05-20 | 中国空气动力研究与发展中心低速空气动力研究所 | Power control method of electric heating ice prevention and removal system based on optical fiber icing detection |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107120721A (en) * | 2017-05-25 | 2017-09-01 | 河北健特建筑安装工程有限公司 | A kind of central heating dynamic gas candidate compensation method |
| CN109976419A (en) * | 2019-02-27 | 2019-07-05 | 武汉中电节能有限公司 | District cooling and heating steam temperature reducing and pressure reducing automatic control system and method |
| CN111027007A (en) * | 2019-12-30 | 2020-04-17 | 天津天大求实电力新技术股份有限公司 | Building characteristic-based heat demand prediction method and system for heat storage and heating system |
-
2020
- 2020-12-08 CN CN202011424106.6A patent/CN112541259B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107120721A (en) * | 2017-05-25 | 2017-09-01 | 河北健特建筑安装工程有限公司 | A kind of central heating dynamic gas candidate compensation method |
| CN109976419A (en) * | 2019-02-27 | 2019-07-05 | 武汉中电节能有限公司 | District cooling and heating steam temperature reducing and pressure reducing automatic control system and method |
| CN111027007A (en) * | 2019-12-30 | 2020-04-17 | 天津天大求实电力新技术股份有限公司 | Building characteristic-based heat demand prediction method and system for heat storage and heating system |
Non-Patent Citations (4)
| Title |
|---|
| 张瑞雪等: "间歇运行供暖系统设计日逐时热负荷附加计算", 《暖通空调》, no. 07, 15 July 2018 (2018-07-15) * |
| 李佳殷等: "基于Elman神经网络的新风负荷预测研究", 《建筑节能》, no. 03, 25 March 2020 (2020-03-25) * |
| 杨兵等: "室内动态/稳态热环境下外围护结构热湿传递的差异分析", 《流体机械》, no. 02, 28 February 2020 (2020-02-28) * |
| 王淞等: "分户计量供暖系统室温及热负荷动态模拟软件研究", 《暖通空调》, no. 02, 15 February 2006 (2006-02-15) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114516403A (en) * | 2022-03-07 | 2022-05-20 | 中国空气动力研究与发展中心低速空气动力研究所 | Power control method of electric heating ice prevention and removal system based on optical fiber icing detection |
| CN114516403B (en) * | 2022-03-07 | 2023-05-05 | 中国空气动力研究与发展中心低速空气动力研究所 | Power control method of electrothermal ice prevention and removal system based on optical fiber icing detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112541259B (en) | 2022-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Toutou et al. | The parametric based optimization framework daylighting and energy performance in residential buildings in hot arid zone | |
| Lapisa et al. | Optimized design of low-rise commercial buildings under various climates–Energy performance and passive cooling strategies | |
| Li et al. | Fast bidirectional building performance optimization at the early design stage | |
| CN110717985B (en) | Construction method of building digital twin platform | |
| Moon et al. | Determining optimum control of double skin envelope for indoor thermal environment based on artificial neural network | |
| Lin et al. | A review on research and development of passive building in China | |
| Moon et al. | Algorithm for optimal application of the setback moment in the heating season using an artificial neural network model | |
| Ferrara et al. | Modelling Zero Energy Buildings: parametric study for the technical optimization | |
| Brun et al. | Behavioural comparison of some predictive tools used in a low-energy building | |
| Ibrahim et al. | Multi-objective optimisation of urban courtyard blocks in hot arid zones | |
| Sick et al. | Dynamic building simulations for the establishment of a Moroccan thermal regulation for buildings | |
| Xia et al. | Analysis and comparison on the potential of low-carbon architectural design strategies | |
| CN112541259B (en) | Self-feedback temperature adjusting method and system for independent heating system | |
| Liu et al. | Simulation analysis and scheme optimization of energy consumption in public buildings | |
| Chen et al. | Assessments of multiple operation strategies in a passive office Building in Cold Region of China | |
| CN106600026A (en) | Residential building energy consumption prediction method suitable for hilly area in east part of Zhejiang province | |
| Yazarlou et al. | Investigation of plans shape and glazing percentage for the energy efficiency of residential buildings | |
| Zhang | Research on building energy efficiency based on energyplus software | |
| Yazdi et al. | Comparing the Thermal Efficiency of Courtyard and Atrium | |
| Mahmoud et al. | Simulation analysis for evaluating smart technique of energy performance in Egypt | |
| Bhiwapurkar et al. | Street geometry and energy conservation of urban buildings in Chicago | |
| Wen et al. | Phenomenon of courtyards being roofed and its significance for building energy efficiency | |
| Zhang et al. | Optimization and Prediction of Energy Consumption, Daylighting, and Thermal Comfort of Buildings in Tropical Areas | |
| Wen | Research on an optimisation control method of large-scale buildings energy saving based on particle swarm optimisation | |
| Heiselberg | Expert Guide: Part 1 Responsive Building Concepts |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221215 Address after: Room 3115, No. 135, Ward Avenue, Ping'an Street, Changqing District, Jinan, Shandong 250300 Patentee after: Shandong Jiqing Technology Service Co.,Ltd. Address before: 250353 University Road, Changqing District, Ji'nan, Shandong Province, No. 3501 Patentee before: Qilu University of Technology |
|
| TR01 | Transfer of patent right |