CN109164707A - A kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm - Google Patents
A kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm Download PDFInfo
- Publication number
- CN109164707A CN109164707A CN201811138708.8A CN201811138708A CN109164707A CN 109164707 A CN109164707 A CN 109164707A CN 201811138708 A CN201811138708 A CN 201811138708A CN 109164707 A CN109164707 A CN 109164707A
- Authority
- CN
- China
- Prior art keywords
- indoor environment
- feedback
- data processing
- neural network
- dpp
- 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
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The indoor environment negative-feedback regu- lation system based on artificial neural network algorithm that the invention discloses a kind of, it is connected including data processing platform (DPP), intelligence control system, indoor environment monitoring system, human thermal sensation's feedback system and elementary item Parameters Input Unit, data processing platform (DPP) with intelligence control system.Indoor environment negative-feedback regu- lation system proposed by the present invention based on artificial neural network algorithm, each weight matrix is obtained after carrying out feedback calculating to environmental parameter and crowd's hotness value of feedback by model, intelligence control system handles weight matrix, it is proposed the scheme of raising human comfort evaluation index, by data processing, the correction value of indoor environment parameter is obtained;Entirety can be monitored indoor environment, realize feedback automatic adjustment, have learning functionality, can automatically derived best indoor environment parameter according to varying environment.
Description
Technical field
The present invention relates to indoor environment negative-feedback regu- lation systems technology fields, in particular to a kind of to be based on artificial neural network
The indoor environment negative-feedback regu- lation system of network algorithm.
Background technique
With the development of economic technology, in China, people couple and the attention rate of own existence environment are gradually reinforced, and compel to make one
For current local environment, more stringent requirements are proposed, and be the requirement to indoor environment.According to statistics, common people 70% with
On time all spend indoors, therefore the superiority and inferiority of indoor environment directly affects the comfort level and health shape of indoor occupant
Condition.Currently, indoor environment is mainly based on traditional monitoring, including the detection of temperature and humidity, gas concentration lwevel." green building is commented
Price card is quasi- " for GB/T 50378-2014 for the higher room of density of personnel, proposition carries out data to indoor gas concentration lwevel
Acquisition, analysis, and the requirement with ventilating system linkage, to guarantee indoor fresh air volume demand, while reaching building energy conservation
Purpose.
At present the shortcomings that the technology: first: at present to Indoor Environment Detection mainly in the research to environment itself, lack with
The linkage of feedback intelligent regulating system.Monitoring system main application is in the collection and displaying of data, mostly without feedback and certainly
Regulating system, it is more single having looped system, and looped system is the secured adjusted mode of program setting,
Without self-learning function.Second: the automatic regulating system of Some Air Conditioning System is mainly fed back according to outdoor temperature and humidity situation,
And lack monitoring to indoor environment itself, and it is especially the absence of and is interacted with personnel in environment, large-scale public construction and personnel in part
There are limitations in density biggish place.
Summary of the invention
More single for this existing looped system of solution, fixed non-adjustable, the no self-learning function of shaping modes uses
There are problems that limitation, the indoor environment negative-feedback based on artificial neural network algorithm that the purpose of the present invention is to provide a kind of
Regulating system, to solve the problems mentioned in the above background technology.
To achieve the above object, the invention provides the following technical scheme: a kind of interior based on artificial neural network algorithm
Environment negative-feedback regu- lation system, including data processing platform (DPP), intelligence control system, indoor environment monitoring system, human thermal sensation
Feedback system and elementary item Parameters Input Unit, data processing platform (DPP) are connected with intelligence control system, intelligence control system with
Indoor environment monitoring system is connected, indoor environment monitoring system, human thermal sensation's feedback system and elementary item parameter input system
System is connected with data processing platform (DPP), and main target is evaluated in real time hot comfort based on user, the hot comfort that will be obtained
Evaluation information feeds back to data processing platform (DPP), and data processing platform (DPP) establishes model, after adjusting model parameter, then feeds back to intelligent control
It is handled in system processed, realizes indoor environment negative-feedback regu- lation.
Preferably, indoor environment monitoring system is passed by temperature-humidity monitoring instrument, gas concentration lwevel monitor and space hold
Sensor composition, temperature-humidity monitoring instrument, gas concentration lwevel monitor and space hold sensor composition are mounted on building interior, temperature
Humidity detection instrument carries out real-time monitoring to indoor temperature and humidity, and gas concentration lwevel monitor carries out the concentration of indoor carbon dioxide
Monitoring, space hold sensor is monitored indoor occupant occupation rate, temperature-humidity monitoring instrument, gas concentration lwevel monitor and
The environmental parameter of space hold sensor monitoring is by network instantaneous transmission to data processing platform (DPP).
Preferably, human thermal sensation's feedback system uses plate, plate and data processing platform (DPP) to pass through network connection, plate
Be placed on the populations such as entrance and information platform enter and leave flowing position, plate be equipped with 5 grades of scale interfaces of ASHRAE hotness, 5
Grade scale is respectively cold, cool, moderate, warm comfortable, and corresponding scale is followed successively by -2, -1,0,1 and 2, and personnel are on plate to comfortable
Degree selection evaluation.
Preferably, elementary item Parameters Input Unit is for inputting climate parameter, item types and project present position
Etc. information, and by information by network transmission to data processing platform (DPP).
Preferably, data processing platform (DPP) obtains each monitoring parameters to human comfort influence degree, comprising: establishes indoor
Thermal and humidity environment comfort level feedback system and algorithm using the back propagation in neural network algorithm, wherein calculating process include with
Lower step:
Step 1): input initial parameter, weight;
Step 2): by forward-propagating, human comfort evaluation index is obtained;
Step 3): comparing with the human comfort evaluation index actually obtained, obtains error;
Step 3): by modifying weight for error back propagation, so that output valve is accurate, closer to actual value;
Preferably, above-mentioned steps 1-5 constantly moves in circles, and obtains reasonable weight and monitoring model, obtains each monitoring
The influence degree of parameters on human comfort level.
Preferably, intelligence control system proposes to improve human comfort on the basis of the model that data processing platform (DPP) is established
The scheme of evaluation index obtains the correction value of indoor air chemical pollution parameter by data processing.Preferably, the intelligent control
System proposes the scheme for improving human comfort evaluation index, passes through data on the basis of the model that data processing platform (DPP) is established
Processing, the correction value for obtaining indoor air chemical pollution parameter drop efficiency while obtaining more excellent human comfort evaluation index
It is low.
Compared with prior art, the beneficial effects of the present invention are: it is proposed by the present invention based on artificial neural network algorithm
Indoor environment negative-feedback regu- lation system passes temperature-humidity monitoring instrument, gas concentration lwevel monitor and space hold by model
The environmental parameter and crowd's hotness value of feedback of sensor monitoring obtain each weight matrix, weight square after carrying out feedback calculating
Battle array feedback proposes the scheme for improving human comfort evaluation index to being handled in intelligence control system, by data processing,
The correction value for obtaining indoor environment parameter, takes equipment directly to adjust indoor environment to environmental optima, without adjusting repeatedly, energy
Effect reduces;Entirety can be monitored indoor environment, realize feedback automatic adjustment, have learning functionality, according to varying environment
It can automatically derived best indoor environment parameter.
Detailed description of the invention
Fig. 1 is overall work block diagram of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, a kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm, including at data
Platform, intelligence control system, indoor environment monitoring system, human thermal sensation's feedback system and elementary item parameter input system
System, data processing platform (DPP) are connected with intelligence control system, and intelligence control system is connected with indoor environment monitoring system, indoor environment
Monitoring system, human thermal sensation's feedback system and elementary item Parameters Input Unit are connected with data processing platform (DPP), main mesh
Mark is evaluated in real time hot comfort based on user, obtained hot comfort evaluation information is fed back to data processing platform (DPP), number
Model is established according to processing platform, after adjusting model parameter, then feeds back to and is handled in intelligence control system, realizes that indoor environment is negative anti-
Feedback is adjusted.
Indoor environment monitoring system is by temperature-humidity monitoring instrument, gas concentration lwevel monitor and space hold sensor group
At temperature-humidity monitoring instrument, gas concentration lwevel monitor and space hold sensor composition are mounted on building interior, temperature and humidity prison
It surveys instrument and real-time monitoring is carried out to indoor temperature and humidity, gas concentration lwevel monitor is monitored the concentration of indoor carbon dioxide,
Space hold sensor is monitored indoor occupant occupation rate, temperature-humidity monitoring instrument, gas concentration lwevel monitor and space
The environmental parameter of take sensor monitoring is by network instantaneous transmission to data processing platform (DPP).
Human thermal sensation's feedback system uses plate, plate and data processing platform (DPP) by network connection, and plate is placed on
The populations such as entrance and information platform enter and leave the position of flowing, and plate is equipped with 5 grades of scale interfaces of ASHRAE hotness, 5 grades of scales
Respectively cold, cool, moderate, warm comfortable, corresponding scale is followed successively by -2, -1,0,1 and 2, and personnel select comfort level on plate
Select evaluation.
Please refer to table one:
5 grades of scales of ASHRAE hotness
Table one:
Hotness | It is cold | It is cool | It is moderate | It is warm | Heat |
Corresponding scale | -2 | -1 | 0 | 1 | 2 |
Elementary item Parameters Input Unit is used to input the information such as climate parameter, item types and project present position,
And information is passed through into network transmission to data processing platform (DPP).
Data processing platform (DPP) obtains each monitoring parameters to human comfort influence degree, and detailed process is as follows:
Indoor Thermal Environment comfort level feedback system is established, using ANN neural network, ANN neural network is using a large amount of sections
Point is connected and is calculated, one specific output function of each node on behalf, also referred to as activation primitive;Between two nodes
Connection represents the weighted value for assigning input signal, also referred to as weight;For simplified model, the BP in ANN neural network can be used
Algorithm (Back Propagation) carries out model construction, and in model foundation, neural network includes three layers, including input layer, hidden
Hide layer and output layer;
Algorithm for several training samples, there is phase in the algorithm using the back propagation in neural network algorithm
Corresponding input value, sample input value pass through a hidden layer forward direction back-propagation, and existing association passes through weight between input value
Matrix embodies, in communication process each time, one layer of output under the influence of weight, by comparing calculate output valve and target value it
Between mean square error, it can be determined that the accuracy of weight, if mean square error be greater than allowable error precision, enter backpropagation
Journey, in back-propagation process, mean square error is counter-propagating to each layer each unit by original route by algorithm, so that each unit connects
By corresponding weight is modified after error amount, by back and forth calculating, until mean square error is in the error range of permission, at this time
Training process terminates, and weight matrix at this time is training result.
Data processing platform (DPP) obtains each monitoring parameters to human comfort influence degree, comprising: establishes the wet ring of Indoor Thermal
Border comfort level feedback system and algorithm are using the back propagation in neural network algorithm, and wherein calculating process includes following step
It is rapid:
Step 1): input initial parameter, weight;
Step 2): by forward-propagating, human comfort evaluation index is obtained;
Step 3): comparing with the human comfort evaluation index actually obtained, obtains error;
Step 3): by modifying weight for error back propagation, so that output valve is accurate, closer to actual value;
Above-mentioned steps 1-5, constantly moves in circles, and obtains reasonable weight and monitoring model, obtains each monitoring parameters pair
The influence degree of human comfort.It constantly moves in circles, obtains reasonable weight and monitoring model, obtain each monitoring parameters pair
The influence degree of human comfort.
Circular is as follows:
Each different environment is set as a training examples
Backpropagation(training_examples,η,nin,nout,nhidden)
Form < x when each training examples in training_examples→, t→> sequence it is even, wherein x→It is network inputs
It is worth vector, t→It is target output value, η is learning efficiency (such as 0.05), ninIt is the quantity of network inputs, nhiddenIt is hidden layer
Unit, noutIt is output unit number.
Input from unit i to unit j is expressed as xji, the weight of unit i to unit j is expressed as wij。
Creation has ninA input, nhiddenA hidden unit, noutThe network of a output unit;
Initializing all network weights is the smallest random value (such as number between -0.05 and 0.05);
Before encountering termination, does and propagate forward;
For each of training examples training_examples < x→, t→>, do backpropagation;
Input is propagated forward along network;
1. example x→Network is inputted, and calculates the output o of each unit u in networku;
Make error along network backpropagation
2. calculating its error term δ for each output unit K of networkk
δk←ok(1-ok)(tk-ok)
3. calculating its error term δ for each hidden unit h of networkh
4. updating each network weight wji
wji←wji+△wji
Wherein: △ wji=η δjxji
Intelligence control system proposes that improving human comfort evaluation refers on the basis of the model that data processing platform (DPP) is established
Target scheme obtains the correction value of indoor air chemical pollution parameter by data processing, refers to obtaining more excellent human comfort evaluation
Target simultaneously, reduces efficiency.
The indoor environment negative-feedback regu- lation system based on artificial neural network algorithm, first using in ANN neural network
BP algorithm (Back Propagation) construct model, in conjunction with indoor environment monitoring data, and indoor crowd is for ring
The human thermal comfort degree evaluation of estimate of border comfort level, is learnt in model by artificial neural networks method, and it is reasonable to obtain
Value of feedback is adjusted indoor environment index by intelligence control system, to maintain environmental degree of comfort in reasonable range
It is interior, while also guaranteeing building energy conservation, system accuracy is improved by constantly trained and study;Model has self-study and self
Perfect appoints you to manage, and initial stage precision may not be high, and post precision can step up after improving;One when due to human thermal sensation
Kind physiology, integrative psychological are felt, are concentrated expression of the people to environmental factor and oneself factor coupling, but due to the multiplicity of people
Property and its subjectivity, itself adjust otherness so that becoming complexity, multiple parameters pair to the degree of recognition of environmental degree of comfort
The influence non-linear relation of human comfort, cannot the single value of feedback linear regulation environmental parameter according to people, such as in difference
In the case where humidity, gas concentration lwevel and personnel's occupation rate, influence of the same temperature to human comfort is different, these ginsengs
The weighing factor of several pairs of human comforts is different, also there is complicated non-linear relation each other, and can be to interior by model
Environmental monitoring data, and indoor crowd carry out integrating non-linear place for the human thermal comfort degree evaluation of estimate of environmental degree of comfort
Reason, different temperature and humidity, gas concentration lwevel and space occupancy rate are corresponding to have a weight, and multiple weight compositions go to weigh
Value matrix, intelligence control system handle weight matrix, propose the scheme for improving human comfort evaluation index, pass through number
According to processing, the correction value of indoor environment parameter is obtained.
In summary: the indoor environment negative-feedback regu- lation system proposed by the present invention based on artificial neural network algorithm is led to
Cross the environmental parameter and crowd that model monitors temperature-humidity monitoring instrument, gas concentration lwevel monitor and space hold sensor
Hotness value of feedback obtains each weight matrix after carrying out feedback calculating, carries out in weight matrix feedback to intelligence control system
Processing proposes the scheme for improving human comfort evaluation index, by data processing, obtains the correction value of indoor environment parameter,
Equipment is taken directly to adjust indoor environment to environmental optima, without adjusting repeatedly, efficiency is reduced;Entirety can to indoor environment into
It goes and monitors, realize feedback automatic adjustment, there is learning functionality, it can automatically derived best indoor environment ginseng according to varying environment
Number.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Anyone skilled in the art in the technical scope disclosed by the present invention, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (7)
1. a kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm, which is characterized in that at data
Platform, intelligence control system, indoor environment monitoring system, human thermal sensation's feedback system and elementary item parameter input system
System, data processing platform (DPP) are connected with intelligence control system, and intelligence control system is connected with indoor environment monitoring system, indoor environment
Monitoring system, human thermal sensation's feedback system and elementary item Parameters Input Unit are connected with data processing platform (DPP), main mesh
Mark is evaluated in real time hot comfort based on user, obtained hot comfort evaluation information is fed back to data processing platform (DPP), number
Model is established according to processing platform, after adjusting model parameter, then feeds back to and is handled in intelligence control system, realizes that indoor environment is negative anti-
Feedback is adjusted.
2. a kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm as described in claim 1, special
Sign is: indoor environment monitoring system is made of temperature-humidity monitoring instrument, gas concentration lwevel monitor and space hold sensor,
Temperature-humidity monitoring instrument, gas concentration lwevel monitor and space hold sensor composition are mounted on building interior, temperature-humidity monitoring
Instrument carries out real-time monitoring to indoor temperature and humidity, and gas concentration lwevel monitor is monitored the concentration of indoor carbon dioxide, empty
Between take sensor indoor occupant occupation rate is monitored, temperature-humidity monitoring instrument, gas concentration lwevel monitor and space account for
The environmental parameter monitored with sensor is by network instantaneous transmission to data processing platform (DPP).
3. a kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm as described in claim 1, special
Sign is: human thermal sensation's feedback system uses plate, plate and data processing platform (DPP) by network connection, and plate is placed on out
The populations such as entrance and information platform enter and leave the position of flowing, and plate is equipped with 5 grades of scale interfaces of ASHRAE hotness, 5 grades of scales point
Wei not be cold, cool, moderate, warm comfortable, corresponding scale is followed successively by -2, -1,0,1 and 2, and personnel comment comfort level selection on plate
Valence.
4. a kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm as described in claim 1, special
Sign is: elementary item Parameters Input Unit is used to input the information such as climate parameter, item types and project present position, and
By information by network transmission to data processing platform (DPP).
5. a kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm as described in claim 1, special
Sign is: data processing platform (DPP) obtains each monitoring parameters to human comfort influence degree, comprising: establishes Indoor Thermal Environment
Comfort level feedback system and algorithm using the back propagation in neural network algorithm, wherein calculating process the following steps are included:
Step 1): input initial parameter, weight;
Step 2): by forward-propagating, human comfort evaluation index is obtained;
Step 3): comparing with the human comfort evaluation index actually obtained, obtains error;
Step 3): by modifying weight for error back propagation, so that output valve is accurate, closer to actual value.
6. a kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm as claimed in claim 5, special
Sign is: above-mentioned steps 1-5 constantly moves in circles, and obtains reasonable weight and monitoring model, obtains each monitoring parameters to people
The influence degree of body comfort level.
7. a kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm as described in claim 1, special
Sign is: intelligence control system, on the basis of the model that data processing platform (DPP) is established, proposes to improve human comfort evaluation index
Scheme, pass through data processing, obtain indoor air chemical pollution parameter correction value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811138708.8A CN109164707A (en) | 2018-09-28 | 2018-09-28 | A kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811138708.8A CN109164707A (en) | 2018-09-28 | 2018-09-28 | A kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109164707A true CN109164707A (en) | 2019-01-08 |
Family
ID=64892861
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811138708.8A Pending CN109164707A (en) | 2018-09-28 | 2018-09-28 | A kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109164707A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109616101A (en) * | 2019-02-12 | 2019-04-12 | 百度在线网络技术(北京)有限公司 | Acoustic training model method, apparatus, computer equipment and readable storage medium storing program for executing |
CN109905489A (en) * | 2019-04-01 | 2019-06-18 | 重庆大学 | Multi-sensor data relevance processing method and system based on data anastomosing algorithm |
CN109946987A (en) * | 2019-03-27 | 2019-06-28 | 吉林建筑大学 | A kind of life of elderly person environment optimization monitoring method Internet-based |
CN112074053A (en) * | 2020-08-24 | 2020-12-11 | 中国建筑科学研究院有限公司 | Lighting equipment regulation and control method and device based on indoor environment parameters |
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 |
CN113268098A (en) * | 2021-06-23 | 2021-08-17 | 上海市建筑科学研究院有限公司 | Indoor environment regulation and control method and system |
CN113790503A (en) * | 2021-11-11 | 2021-12-14 | 成都联帮医疗科技股份有限公司 | Dispersion oxygen supply terminal machine capable of intelligently adjusting oxygen supply state and control method thereof |
CN114322271A (en) * | 2021-12-06 | 2022-04-12 | 青岛海尔空调器有限总公司 | Control method and device for air conditioner, air conditioner and storage medium |
CN114580071A (en) * | 2022-04-28 | 2022-06-03 | 江苏南通冠仟新材料科技有限公司 | Adjacent floor shock insulation damping comfort evaluation method based on computer aided design |
CN116538654A (en) * | 2023-07-06 | 2023-08-04 | 中国航空工业集团公司金城南京机电液压工程研究中心 | Self-adaptive space thermal environment intelligent control method |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101140450A (en) * | 2006-09-08 | 2008-03-12 | 香港中文大学精密工程研究所 | Energy conservation type heat comfortable controller and control method |
CN204085569U (en) * | 2014-09-18 | 2015-01-07 | 湖南师范大学 | A kind of hot comfort instrument for measuring index based on Internet of Things and neural network |
CN104374053A (en) * | 2014-11-25 | 2015-02-25 | 珠海格力电器股份有限公司 | Intelligent control method, device and system |
CN204853818U (en) * | 2015-06-26 | 2015-12-09 | 苏州中科院全周期绿色建筑研究院有限公司 | Interactive air conditioner environment comfort level detection device |
CN105910225A (en) * | 2016-04-18 | 2016-08-31 | 浙江大学 | Air conditioner load control system and method based on personnel information detection |
CN106322656A (en) * | 2016-08-23 | 2017-01-11 | 海信(山东)空调有限公司 | Air conditioner control method, server and air conditioner system |
CN106322657A (en) * | 2016-08-23 | 2017-01-11 | 海信(山东)空调有限公司 | Air conditioner control method, air conditioner controller and air conditioner system |
CN106352475A (en) * | 2016-08-23 | 2017-01-25 | 海信(山东)空调有限公司 | Training sample collection method and device of air conditioner neutral network and air conditioning system |
WO2017076433A1 (en) * | 2015-11-03 | 2017-05-11 | Siemens Aktiengesellschaft | Intelligent heat, ventilation, and air conditioning system |
CN107062540A (en) * | 2017-04-01 | 2017-08-18 | 深圳达实智能股份有限公司 | A kind of hospital clinic thermal comfort ballot control method, device, system |
-
2018
- 2018-09-28 CN CN201811138708.8A patent/CN109164707A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101140450A (en) * | 2006-09-08 | 2008-03-12 | 香港中文大学精密工程研究所 | Energy conservation type heat comfortable controller and control method |
CN204085569U (en) * | 2014-09-18 | 2015-01-07 | 湖南师范大学 | A kind of hot comfort instrument for measuring index based on Internet of Things and neural network |
CN104374053A (en) * | 2014-11-25 | 2015-02-25 | 珠海格力电器股份有限公司 | Intelligent control method, device and system |
CN204853818U (en) * | 2015-06-26 | 2015-12-09 | 苏州中科院全周期绿色建筑研究院有限公司 | Interactive air conditioner environment comfort level detection device |
WO2017076433A1 (en) * | 2015-11-03 | 2017-05-11 | Siemens Aktiengesellschaft | Intelligent heat, ventilation, and air conditioning system |
CN105910225A (en) * | 2016-04-18 | 2016-08-31 | 浙江大学 | Air conditioner load control system and method based on personnel information detection |
CN106322656A (en) * | 2016-08-23 | 2017-01-11 | 海信(山东)空调有限公司 | Air conditioner control method, server and air conditioner system |
CN106322657A (en) * | 2016-08-23 | 2017-01-11 | 海信(山东)空调有限公司 | Air conditioner control method, air conditioner controller and air conditioner system |
CN106352475A (en) * | 2016-08-23 | 2017-01-25 | 海信(山东)空调有限公司 | Training sample collection method and device of air conditioner neutral network and air conditioning system |
CN107062540A (en) * | 2017-04-01 | 2017-08-18 | 深圳达实智能股份有限公司 | A kind of hospital clinic thermal comfort ballot control method, device, system |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109616101A (en) * | 2019-02-12 | 2019-04-12 | 百度在线网络技术(北京)有限公司 | Acoustic training model method, apparatus, computer equipment and readable storage medium storing program for executing |
CN109946987A (en) * | 2019-03-27 | 2019-06-28 | 吉林建筑大学 | A kind of life of elderly person environment optimization monitoring method Internet-based |
CN109905489A (en) * | 2019-04-01 | 2019-06-18 | 重庆大学 | Multi-sensor data relevance processing method and system based on data anastomosing algorithm |
CN112074053A (en) * | 2020-08-24 | 2020-12-11 | 中国建筑科学研究院有限公司 | Lighting equipment regulation and control method and device based on indoor environment parameters |
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 |
CN113268098A (en) * | 2021-06-23 | 2021-08-17 | 上海市建筑科学研究院有限公司 | Indoor environment regulation and control method and system |
CN113790503A (en) * | 2021-11-11 | 2021-12-14 | 成都联帮医疗科技股份有限公司 | Dispersion oxygen supply terminal machine capable of intelligently adjusting oxygen supply state and control method thereof |
CN114322271A (en) * | 2021-12-06 | 2022-04-12 | 青岛海尔空调器有限总公司 | Control method and device for air conditioner, air conditioner and storage medium |
CN114322271B (en) * | 2021-12-06 | 2024-06-18 | 青岛海尔空调器有限总公司 | Control method and device for air conditioner, air conditioner and storage medium |
CN114580071A (en) * | 2022-04-28 | 2022-06-03 | 江苏南通冠仟新材料科技有限公司 | Adjacent floor shock insulation damping comfort evaluation method based on computer aided design |
CN116538654A (en) * | 2023-07-06 | 2023-08-04 | 中国航空工业集团公司金城南京机电液压工程研究中心 | Self-adaptive space thermal environment intelligent control method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109164707A (en) | A kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm | |
CN111210082B (en) | Precipitation prediction method based on optimized BP neural network algorithm | |
CN108916986B (en) | Information physical fusion secondary pipe network variable flow hydraulic balance regulation and control method and system | |
CN109270842B (en) | Bayesian network-based regional heat supply model prediction control system and method | |
CN108694467B (en) | Method and system for predicting line loss rate of power distribution network | |
CN104359192B (en) | The energy-conservation comfortable personalized control system of a kind of indoor environment based on data and method | |
CN105320184B (en) | Building Indoor Environment intelligent monitor system | |
CN106765959A (en) | Heat-air conditioner energy-saving control method based on genetic algorithm and depth B P neural network algorithms | |
CN106920006A (en) | A kind of subway station air conditioning energy consumption Forecasting Methodology based on ISOA LSSVM | |
CN106991504B (en) | Building energy consumption prediction method and system based on subentry measurement time sequence and building | |
CN110332647A (en) | Subway underground station Load Prediction method and air-conditioning system | |
CN102563808A (en) | Automatic control method of indoor environment comfort level | |
CN106529719A (en) | Method of predicting wind power of wind speed fusion based on particle swarm optimization algorithm | |
CN111520878A (en) | Air conditioner temperature control system based on RBF neural network and control method thereof | |
CN106026084B (en) | A kind of AGC power dynamic allocation methods based on virtual power generation clan | |
CN106371316B (en) | Water island dosing On-Line Control Method based on PSO LSSVM | |
CN109993463A (en) | A kind of engineering quality control evaluation method of pipe gallery | |
CN112524751A (en) | Dynamic air conditioning system energy consumption prediction model construction and prediction method and device | |
Dou et al. | Long-term weather prediction based on GA-BP neural network | |
Sun et al. | Energy consumption optimization of building air conditioning system via combining the parallel temporal convolutional neural network and adaptive opposition-learning chimp algorithm | |
CN114200839A (en) | Office building energy consumption intelligent control model for dynamic monitoring of coupled environmental behaviors | |
CN114838452B (en) | Intelligent air valve applied to variable air volume system, system and control method | |
Jin et al. | Prediction of Indoor Air Temperature Based on Deep Learning. | |
Zhang et al. | Comparing the linear and logarithm normalized artificial neural networks in inverse design of aircraft cabin environment | |
CN115408930A (en) | Load prediction method for subway ventilation air-conditioning system |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190108 |
|
RJ01 | Rejection of invention patent application after publication |