CN102563808B - Automatic control method of indoor environment comfort level - Google Patents
Automatic control method of indoor environment comfort level Download PDFInfo
- Publication number
- CN102563808B CN102563808B CN201210007218.0A CN201210007218A CN102563808B CN 102563808 B CN102563808 B CN 102563808B CN 201210007218 A CN201210007218 A CN 201210007218A CN 102563808 B CN102563808 B CN 102563808B
- Authority
- CN
- China
- Prior art keywords
- comfort level
- indoor
- indoor environment
- temperature
- 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.)
- Expired - Fee Related
Links
Abstract
The invention relates to the technical field of indoor environment regulation, and provides an automatic control method of the indoor environment comfort level. According to the method, a three-layer BP (back-propagation) neural network is selected as a model. The method comprises the following steps of: 1), collecting the current actual environment data as sample data; 2), building the model by the sample data based on the three-layer feed-forward BP neural network; 3), setting an optimal value and a range of an SET* index by using model-based prediction and control; 4), controlling an air-conditioning system, combining with the optical value and the range of the SET* index to process the current data collected in real time, and generating a signal for controlling the air-conditioning system, so as to realize real-time control of an environment control device. According to the automatic control method, the defect of complicated iterative operation in the traditional model is overcome; the convergence rate is increased by an improved L-M algorithm, and the prediction mode has high validity and small error.
Description
Technical field
The invention belongs to indoor environment regulation technology field, particularly a kind of autocontrol method of indoor environment comfort level.
Background technology
Modern society people spend indoor more than 85% time, and the quality of indoor environment has direct impact to the physical and mental health of human body, comfort level and operating efficiency, so people are also more and more high for the requirement of environment.At present to take the two-node model theory that human body temperature regulates be basis to the SET* index (standard effective temperature (SET)) of extensive use ASHRAE standard, the Physical Process Analyses at heat transfer in human body draws Thermal Synthetic comfort level index, the heat reflection of human body under prediction thermal environment, weigh with control room in environmental degree of comfort.
SET* index is the hot comfort index according to physiological reaction model, and influence factor mainly comprises air themperature, air humidity, air velocity and radiation temperature.These environmental factors are not variablees completely independently, but interact, inseparable.Have non-linear, time the complicated characteristic such as become.The prior art mainly computing that iterates of the impacts such as temperature and humidity by parameters on human skins such as air themperature, humidity, wind speed, mean radiant temperatures is determined SET* index, calculation of complex, can not be real-time determine, is therefore difficult to meet the requirement that air-conditioning system is controlled in real time.Having a lot of research is all that the value within the specific limits of supposing sample data obtains, but the sample data that actual measurement obtains is more conducive to the training to SET* index model.
Summary of the invention
The object of the invention is to overcome the shortcoming and defect of prior art, a kind of weighed energy loss and indoor comfort degree are provided, to reach best optimal policy, realize a kind of method of automatic indoor environmental condition control.
Object of the present invention is achieved through the following technical solutions:
A method for establishing model based on indoor environment comfort level, comprises the following steps:
1) environmental data that gathers current reality is as sample data;
This part mainly comprises the data acquisition of outdoor temperature, relative humidity, mean radiant temperature and wind speed envirment factor, indoor temperature, relative humidity, mean radiant temperature, wind speed envirment factor data acquisition.Corresponding SET* index is applied traditional iterative algorithm and is calculated.
2) utilize sample data to set up based on three layers of feed-forward type BP neural network model;
Three layers of feed-forward type BP network that described model is set up comprise input layer, hidden layer and three parts of output layer.The input of model comprises control inputs amount and disturbance input amount, and control inputs amount is indoor environmental factor, comprises, indoor temperature, relative humidity, mean radiant temperature, wind speed; Disturbance input amount is outdoor environmental factor, comprises outdoor temperature, relative humidity, mean radiant temperature, wind speed.Output is SET* desired value.The node of hidden layer is elected 6 as.
3) adopt the PREDICTIVE CONTROL based on model to set SET* index optimal value and scope;
Model Predictive Control mainly comprises process model building, definition target function, optimizes target function and finite time-domain rolling calculation.Process model building is the behavior that utilizes the following output signal of data prediction of input signal and output signal; Optimization in PREDICTIVE CONTROL is the rolling optimization of a kind of limited period, and it is not that an off-line carries out, but repeatedly carries out online, i.e. so-called rolling optimization.In each sampling instant, optimize index only relate to from this constantly the following limited time, and to next sampling instant, this optimization was passed forward during the period simultaneously.
4) Air-condition system control: in conjunction with SET* index optimal value and scope to Real-time Collection to current data process, produce the signal of controlling air-conditioning system, realize the automatic control of indoor comfort degree.
The data that part of data acquisition arrives Real-time Collection are through after processing, storage, demonstration and management, model is according to every data analysis control algolithm, produce a control signal of optimizing comfort level and energy consumption minimum, this control signal is sent to slave computer, slave computer selects single-chip microcomputer to control air-conditioning system and fan system, realizes the control of indoor comfort degree.
The present invention selects SET* index to replace the hot comfort of human body for controlling target, air themperature, humidity, wind speed and the functional relation of mean radiant temperature environmental variance to SET* have been set up, thereby determine the model structure of the indoor environment factor, and utilize least square method of recursion to carry out the identification of model parameter to the indoor environment temperature system under gravity-flow ventilation condition and air-conditioning effect, set up the reliable Mathematical Modeling of reaction indoor environment, thereby reach suitable comfort level and minimum energy consumption.
The relative prior art of the present invention, has fast convergence rate, and forecast model validity is high, error is little, can realize system in real time and the advantage of automatically controlling.
The specific embodiment
Below in conjunction with embodiment, enforcement of the present invention is further described, but enforcement of the present invention is not limited to this.
A method for establishing model based on indoor environment comfort level, comprises the following steps:
1) environmental data that gathers current reality is as sample data;
2) utilize sample data to set up based on three layers of feed-forward type BP neural network model;
3) adopt the PREDICTIVE CONTROL based on model to set SET* index optimal value and scope;
4) Air-condition system control: in conjunction with SET* index optimal value and scope to Real-time Collection to current data process, produce the signal of controlling air-conditioning system, realize the automatic control of indoor comfort degree.
The environmental data of described step 1) comprises indoor temperature, relative humidity, mean radiant temperature and wind speed, also comprises outdoor temperature, relative humidity, mean radiant temperature and wind speed and current SET* desired value.
Described step 2) BP neutral net comprises input layer, hidden layer and output layer.Input layer comprises control inputs amount and disturbance input amount; Control inputs amount is indoor temperature, relative humidity, mean radiant temperature and wind speed; Disturbance input amount is outdoor temperature, relative humidity, mean radiant temperature and wind speed.Output layer is SET* index.The node of hidden layer is 6.
Adopt least square method of recursion algorithm to BP neutral net is trained, output layer and corresponding input layer are contrasted, until the mean square error of network training reaches requirement, determine weights and the threshold value of each layer.
Process model building is the behavior that utilizes data prediction output signal future of input signal and output signal, determine prediction time domain Np, then by output signal, reference signal and control signal, define corresponding performance function, for control signal being applied to PREDICTIVE CONTROL process, determine and control time domain Nu, by being carried out to some, control signal and output variable limit optimization method, the control signal calculating by equation is applied in the middle of real process, in next step, all algorithm repeats rolling calculation.
Optimization in PREDICTIVE CONTROL is the rolling optimization of a kind of limited period, and it is not that an off-line carries out, but repeatedly carries out online, i.e. so-called rolling optimization.In each sampling instant, optimize index only relate to from this constantly the following limited time, and to next sampling instant, this optimization was passed forward during the period simultaneously.Make like this to optimize calculating more accurate.So PREDICTIVE CONTROL is not to adopt the optimization index identical to the overall situation, but each time be carved with an optimization aim function with respect to this moment.Relative form at different time optimization object functions is identical, but its absolute form is not identical, because included time zone is different.
Indoor environment system is non-linear a, close coupling, strongly disturbing dynamical system, its input and output always in time become state, based on thermal balance, carry out the Mathematical Modeling that deriving analysis obtains, be difficult to determine model parameter, be difficult to be applied to the requirement of indoor environmental condition control.Experimental modeling is the system inputoutput data according to experiment measuring, carried out analyzing and processing and obtained reflecting system model static state and dynamic characteristic, by the structure of some linearization technique derivation models, then with a model, carry out matching, model parameter is carried out to identification.
Indoor environment hot comfort depends mainly on indoor climate condition, the heat exchange of human body and environment.Indoor environment is regarded dynamic many single-input single-output system (SISO system)s (MIMO) as, comprise the heat exchange of human body and environment, indoor air temperature, wind speed, relative humidity, mean radiant temperature, outdoor temperature, humidity, wind speed, intensity of illumination or mean radiant temperature etc.
Owing to being difficult to accurately measure the energy of human body and environment heat exchange, therefore only when calculating human comfort index S ET*, consider the variable relevant to human body, feature for the indoor environment factor, take temperature as environment Main Factors, set up the model of the room main environment factor of gravity-flow ventilation and air-conditioning system effect.
Approach For Identification of Model Structure subject matter is determining of rank, comprises model structure parameter definite of each polynomial order and pure hysteresis in indoor environment factor model.According to the data that measure, selected different orders carry out parameter Estimation, obtain the model equation of different orders, utilize the statistical property of least-squares estimation to determine the true order of model.
Claims (6)
1. the method for establishing model based on indoor environment comfort level, is characterized in that comprising the following steps:
1) environmental data that gathers current reality is as sample data;
2) utilize sample data to set up based on three layers of feed-forward type BP neural network model;
3) adopt the PREDICTIVE CONTROL (MBPC) based on above-mentioned model to be applied in the middle of indoor environmental condition control system, set respectively comfort level SET* index optimal value and SET* value scope;
4) Air-condition system control: in conjunction with SET* index optimal value and set SET* value scope to Real-time Collection to current data process, produce the signal of control air-conditioning system, realize the automatic control of indoor comfort degree;
The environmental data of described step 1) comprises indoor temperature, relative humidity, mean radiant temperature, wind speed, also comprises outdoor temperature, relative humidity, mean radiant temperature and wind speed;
Described sample data also comprises based on current indoor temperature, relative humidity, mean radiant temperature and wind speed, the current SET* desired value of utilizing traditional iterative algorithm to calculate.
2. the method for establishing model based on indoor environment comfort level according to claim 1, is characterized in that described step 2) BP neutral net comprise input layer, hidden layer and output layer.
3. the method for establishing model based on indoor environment comfort level according to claim 2, is characterized in that described input layer comprises control inputs amount and disturbance input amount; Control inputs amount is indoor temperature, relative humidity, mean radiant temperature and wind speed; Disturbance input amount is outdoor temperature, relative humidity, mean radiant temperature and wind speed.
4. the method for establishing model based on indoor environment comfort level according to claim 3, is characterized in that described output layer is SET* index.
5. the method for establishing model based on indoor environment comfort level according to claim 2, the node that it is characterized in that described hidden layer is 6.
6. according to the method for establishing model based on indoor environment comfort level one of claim 1 ~ 5 Suo Shu, it is characterized in that adopting least square method of recursion algorithm to train BP neutral net, output layer and corresponding input layer are contrasted, until the mean square error of network training reaches requirement, determine weights and the threshold value of each layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210007218.0A CN102563808B (en) | 2012-01-11 | 2012-01-11 | Automatic control method of indoor environment comfort level |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210007218.0A CN102563808B (en) | 2012-01-11 | 2012-01-11 | Automatic control method of indoor environment comfort level |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102563808A CN102563808A (en) | 2012-07-11 |
| CN102563808B true CN102563808B (en) | 2014-02-26 |
Family
ID=46409924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210007218.0A Expired - Fee Related CN102563808B (en) | 2012-01-11 | 2012-01-11 | Automatic control method of indoor environment comfort level |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102563808B (en) |
Families Citing this family (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207564B (en) * | 2012-12-03 | 2015-09-09 | 北京华亿九州科技有限公司 | Based on building energy-saving compounding analysis method and the system of sliding moding structure model |
| CN103196206B (en) * | 2013-04-12 | 2015-07-01 | 南京物联传感技术有限公司 | Indoor simulation method for generating natural air |
| CN104075402A (en) * | 2014-06-19 | 2014-10-01 | 珠海格力电器股份有限公司 | Intelligent air conditioner control method and system |
| CN104359192B (en) * | 2014-11-19 | 2016-12-07 | 山东建筑大学 | The energy-conservation comfortable personalized control system of a kind of indoor environment based on data and method |
| CN104490371B (en) * | 2014-12-30 | 2016-09-21 | 天津大学 | A kind of thermal comfort detection method based on human body physiological parameter |
| CN106530649B (en) * | 2016-10-25 | 2019-12-06 | 北京物资学院 | Early warning method and system for healthy use of computer |
| CN106707757A (en) * | 2017-01-23 | 2017-05-24 | 中国农业大学 | Dynamic regulation and control method and system for irrigation time |
| CN108459886A (en) * | 2017-12-18 | 2018-08-28 | 珠海格力电器股份有限公司 | The determination method and apparatus of indoor environment state |
| CN108260332B (en) * | 2018-01-26 | 2020-06-30 | 江苏泽镔信息科技有限公司 | Thermal management control device and method |
| CN108050672B (en) * | 2018-01-26 | 2020-12-22 | 江苏泽镔信息科技有限公司 | Temperature regulation system and method |
| CN108426349B (en) * | 2018-02-28 | 2020-04-17 | 天津大学 | Air conditioner personalized health management method based on complex network and image recognition |
| CN108763730B (en) * | 2018-05-24 | 2022-08-12 | 浙江农林大学 | Method, system, terminal and medium for screening street trees based on thermal comfort indexes |
| CN109028480B (en) * | 2018-06-08 | 2021-08-20 | 杭州博联智能科技股份有限公司 | Constant temperature and humidity control system and method thereof |
| CN110837229B (en) * | 2018-08-17 | 2021-06-29 | 珠海格力电器股份有限公司 | Control method and device for household appliance |
| CN109375508B (en) * | 2018-10-31 | 2021-06-18 | 广州龙越自动化设备有限公司 | Automatic control method and system for customizing functional module based on environmental parameters |
| CN111365828A (en) * | 2020-03-06 | 2020-07-03 | 上海外高桥万国数据科技发展有限公司 | Model prediction control method for realizing energy-saving temperature control of data center by combining machine learning |
| CN112097378A (en) * | 2020-08-21 | 2020-12-18 | 深圳市建滔科技有限公司 | Air conditioner comfort level adjusting method based on feedforward neural network |
| CN112231812B (en) * | 2020-10-15 | 2022-12-09 | 乌江渡发电厂 | Intelligent ventilation control method and system for underground powerhouse of hydropower station |
| CN112308140A (en) * | 2020-10-30 | 2021-02-02 | 上海市建筑科学研究院有限公司 | Indoor environment quality monitoring method and terminal |
| CN112506059B (en) * | 2020-12-07 | 2022-09-16 | 常州常工电子科技股份有限公司 | Classroom self-adaptive control system based on energy-saving model of personal sensory comfort |
| CN112947637B (en) * | 2021-01-29 | 2022-06-24 | 阜阳小欧智能科技有限公司 | Office environment intelligent regulation system |
| CN113485498B (en) * | 2021-07-19 | 2022-10-18 | 北京工业大学 | Indoor environment comfort level adjusting method and system based on deep learning |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1167914C (en) * | 2002-12-05 | 2004-09-22 | 上海交通大学 | Individuality air conditioner |
| CN1301387C (en) * | 2004-06-04 | 2007-02-21 | 广东科龙电器股份有限公司 | Noise source identifying method for air-conditioner based on nervous network |
| CN100406809C (en) * | 2004-10-12 | 2008-07-30 | 株式会社日立制作所 | Air conditioning system |
| CN102110243A (en) * | 2009-12-23 | 2011-06-29 | 新奥特（北京）视频技术有限公司 | Method for predicting human comfort |
-
2012
- 2012-01-11 CN CN201210007218.0A patent/CN102563808B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN102563808A (en) | 2012-07-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102563808B (en) | Automatic control method of indoor environment comfort level | |
| Kim et al. | Predictions of electricity consumption in a campus building using occupant rates and weather elements with sensitivity analysis: Artificial neural network vs. linear regression | |
| Liu et al. | A neural network evaluation model for individual thermal comfort | |
| Li et al. | Dynamic modeling and control of a direct expansion air conditioning system using artificial neural network | |
| Liang et al. | Design of intelligent comfort control system with human learning and minimum power control strategies | |
| CN106842914B (en) | Temperature control energy-saving processing method, device and system | |
| Zou et al. | Model predictive control based on particle swarm optimization of greenhouse climate for saving energy consumption | |
| CN103912966A (en) | Optimal control method for ground source heat pump refrigerating system | |
| KR20200034023A (en) | A method for creating demand response determination model for hvac system and a method for demand response | |
| CN107276069A (en) | Approximate the polymerization modeling method and system of a kind of area power grid resident temperature control load | |
| CN106152387B (en) | A kind of detection method for indoor thermal comfort | |
| Lu et al. | A hybrid numerical-neural-network model for building simulation: A case study for the simulation of unheated and uncooled indoor temperature | |
| Li et al. | A generic approach to calibrate building energy models under uncertainty using bayesian inference | |
| del Mar Castilla et al. | A multivariable nonlinear MPC control strategy for thermal comfort and indoor-air quality | |
| Ren et al. | Developing a collaborative control strategy of a combined radiant floor cooling and ventilation system: A PMV-based model | |
| CN106403162A (en) | Local heat comfort control method, local heat comfort controller and control system | |
| Cheng et al. | A novel data-driven air balancing method with energy-saving constraint strategy to minimize the energy consumption of ventilation system | |
| JP6343499B2 (en) | Energy management system | |
| Berouine et al. | A predictive control approach for thermal energy management in buildings | |
| Sha et al. | A control strategy of heating system based on adaptive model predictive control | |
| CN107168066A (en) | A kind of greenhouse self-adaptation control method | |
| Kciuk et al. | Design and modeling of intelligent building office and thermal comfort based on probabilistic neural network | |
| Yang | Optimization of operation times of a heating system in office building | |
| CN109840307A (en) | A kind of indoor temperature and humidity field quick predict system and method | |
| Yao et al. | Research on the BPNN in the prediction of PMV |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140226 Termination date: 20210111 |