CN105698861A - Indoor environment comfort level evaluation method - Google Patents
Indoor environment comfort level evaluation method Download PDFInfo
- Publication number
- CN105698861A CN105698861A CN201610125058.8A CN201610125058A CN105698861A CN 105698861 A CN105698861 A CN 105698861A CN 201610125058 A CN201610125058 A CN 201610125058A CN 105698861 A CN105698861 A CN 105698861A
- Authority
- CN
- China
- Prior art keywords
- indoor environment
- parameter
- svm
- comfort level
- environment
- 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
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
Abstract
The invention discloses an indoor environment comfort level evaluation method, which includes the steps of: collecting indoor environment parameters which include temperature and humidity, wind speed, air quality, noise, and illumination parameters; performing model training by taking the indoor environment parameters as input, and taking detected physiological parameters as output, and using epsilon-SVM (Support Vector Machines); and performing comfort level on-line evaluation through a trained epsilon-SVM model. The indoor environment comfort level evaluation method takes human physiological feelings as an evaluation standard, obtains the comfort level, comprehensively considers the influences of the thermal environment, the air quality environment, the sound environment, and optical environment factors, and has good practicability.
Description
Technical field
The present invention relates to the evaluation methodology of indoor environment comfort level。
Background technology
Along with improving constantly of people's living standard, the comfortableness of indoor environment is required also more and more higher by people。The comfort level of indoor environment is considered from hot comfort aspect mostly, and has formulated the standardized method ISO7730 of indoor thermal environment evaluation and measurement, have employed PMV-PPD index and describe and evaluate thermal environment in IS07730 standard。PMV index is the meansigma methods being in the colony in thermal environment for hotness, and PPD index is for the unsatisfied number percent of thermal environment。Affect and six factors of PMV-PPD index have four ambient parameters (dry-bulb temperature, relative humidity, WBGT, mild wind speed) and two human parameterss (drcssing index, metabolism rate)。PMV and PPD value can be calculated according to above six parameters, and ISO7730 gives clear and definite computing formula, but the method does not consider the impact of air ambient, luminous environment and acoustic environment etc.。
In indoor environment Comfort Evaluation model, at present through frequently with intelligent algorithm, such as the comprehensive evaluation model based on neutral net, this model has adaptivity and the strong feature of learning capacity, but there is also network structure to select difficulty, cross study and it is difficult to ensure that problems such as global optimums, be unfavorable for the foundation of identification model and extensive application。Evaluation model based on fuzzy theory, utilize maximum membership degree function and fuzzy matrix for assessment to complete overall merit, but fuzzy theory has the defect that it is fatal, namely each index weights determined by each expert is with certain subjectivity, do not meet the principle of science, and in some cases, the determination of membership function has certain difficulty。Based on support vector machine (SupportVectorMachines, SVM) model, it is the VC dimension theory in a kind of Corpus--based Method theory of learning and a kind of new machine learning method proposed on structural risk minimization principle, and this model ensure that the minimax solution found is exactly the optimal solution of the overall situation in fact。Therefore, this model can solve small sample, high dimension and nonlinear problem preferably, has the advantages such as global optimum, simple in construction, extensive (popularization) ability be strong。
Summary of the invention
For solving above-mentioned technical problem, it is an object of the invention to provide a kind of indoor comfort degree Intelligent Evaluation method of energy comprehensive characterization thermal environment, air quality environment, sound and luminous environment。
The purpose of the present invention is realized by following technical scheme:
A kind of indoor environment Comfort Evaluation method, the method includes:
Gathering indoor environment parameter, described ambient parameter includes humiture, wind speed, air quality, noise and illumination parameter;
Using indoor environment parameter as the physiological parameter inputting, detecting as output, ε-SVM is utilized to carry out model training;
Comfort level on-line evaluation is carried out by the ε-SVM model trained。
Compared with prior art, one or more embodiments of the invention can have the advantage that
It is the ambient parameters such as humiture, wind speed, air quality, noise and illumination that sensor acquisition is arrived as input parameter, utilize experiment to obtain physiological parameter as output training ε-SVM model, utilize the ε-SVM model that training obtains can obtain the comfortable angle value of comprehensive indoor environment。The present invention is felt as evaluation criterion with the physiology of people, the comfort level obtained, the comprehensive consideration impact of the factors such as thermal environment, air quality environment, acoustic environment and luminous environment, has good practicality。
Accompanying drawing explanation
Fig. 1 is ambient parameter provided by the invention detection system schematic;
Fig. 2 is indoor environment Comfort Evaluation flow chart provided by the invention;
Fig. 3 is hand mean temperature and the reality of comfort level, the matched curve comparison diagram of the present invention。
Detailed description of the invention
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with embodiment and accompanying drawing, the present invention is described in further detail。
Present embodiments provide a kind of indoor environment Comfort Evaluation method, the method is the ambient parameters such as humiture, wind speed, air quality, noise and the illumination sensor acquisition arrived as input parameter, (as shown in Figure 1, the collection of ambient parameter is respectively through Temperature Humidity Sensor, air velocity transducer, air mass sensor, noise transducer and optical sensor) utilize experiment to obtain physiological parameter as output training ε-SVM model, use the ε-SVM model that training obtains can obtain the comfortable angle value of comprehensive indoor environment。Specific implementation process is as in figure 2 it is shown, include:
Step 10 gathers indoor environment parameter, and described ambient parameter includes humiture, wind speed, air quality, noise and illumination parameter;
Indoor environment parameter as the physiological parameter inputting, detecting as output, is utilized ε-SVM to carry out model training by step 20;
Determine the RBF kernel function of ε-SVM modelLoss function parameter isWithWherein x '=0.2, σ is the standard deviation of input sample, and l is sample number,Average, σ is exported for training sampleyFor output valve standard deviation。
Step 30 carries out comfort level on-line evaluation by the ε-SVM model trained;
By sensor acquisition indoor temperature and humidity, wind speed, air quality, noise and illumination parameter, constitute vectorAs input data, whereinFor one group of data that Sensor monitoring arrives;Utilize the model trained to carry out on-line evaluation, utilize formula:
F (y)=-0.5y4+25.4y3-560.1y2+4609.6y(1)
Can obtaining the comfortable angle value of change between [0,1], in formula, y is the output of ε-SVM model。
The matched curve of formula (1) is as shown in Figure 3。
The technical scheme provided by above-described embodiment can be seen that, the present invention is the ambient parameters such as humiture, wind speed, air quality, noise and the illumination sensor acquisition arrived as input parameter, utilize experiment to obtain physiological parameter as output training ε-SVM model, use the ε-SVM model that training obtains can obtain the comfortable angle value of comprehensive indoor environment。The present invention is felt as evaluation criterion with the physiology of people, the comfort level obtained, the comprehensive consideration impact of the factors such as thermal environment, air quality environment, acoustic environment and luminous environment, has good practicality。
Although the embodiment that disclosed herein is as above, but described content is only to facilitate the embodiment understanding the present invention and adopt, is not limited to the present invention。Technical staff in any the technical field of the invention; under the premise without departing from the spirit and scope that disclosed herein; any amendment and change can be done in the formal and details implemented; but the scope of patent protection of the present invention, still must be as the criterion with the scope that appending claims defines。
Claims (4)
1. an indoor environment Comfort Evaluation method, it is characterised in that described method includes:
Gathering indoor environment parameter, described ambient parameter includes humiture, wind speed, air quality, noise and illumination parameter;
Using indoor environment parameter as the physiological parameter inputting, detecting as output, ε-SVM is utilized to carry out model training;
Comfort level on-line evaluation is carried out by the ε-SVM model trained。
2. indoor environment Comfort Evaluation method as claimed in claim 1, it is characterized in that, the described physiological parameter detected obtains according to experimental technique, and described parameter includes: detection people is hand mean skin temperature under different humitures, wind speed, air quality, noise and photoenvironment parameter。
3. indoor environment Comfort Evaluation method as claimed in claim 1, it is characterised in that the described ε of utilization-SVM carries out model training and includes:
The kernel function of ε-SVM model is RBF kernel functionLoss function parameterWithWherein x '=0.2, σ is the standard deviation of input sample, and l is sample number,Average, σ is exported for training sampleyFor output valve standard deviation。
4. indoor environment Comfort Evaluation method as claimed in claim 1, it is characterised in that the described ε-SVM model by training carries out comfort level on-line evaluation and includes:
By the indoor temperature and humidity gathered, wind speed, air quality, noise and illumination parameter, constitute vectorAs mode input data, model output valve y can be obtained, utilize formula:
F (y)=-0.5y4+25.4y3-560.1y2+4609.6y
Obtain the comfortable angle value of change between [0,1];Wherein, y is the output of ε-SVM model。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610125058.8A CN105698861A (en) | 2016-03-04 | 2016-03-04 | Indoor environment comfort level evaluation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610125058.8A CN105698861A (en) | 2016-03-04 | 2016-03-04 | Indoor environment comfort level evaluation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105698861A true CN105698861A (en) | 2016-06-22 |
Family
ID=56220761
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610125058.8A Pending CN105698861A (en) | 2016-03-04 | 2016-03-04 | Indoor environment comfort level evaluation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105698861A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106371377A (en) * | 2016-11-21 | 2017-02-01 | 上海电机学院 | Intelligent detection device for internal environment quality |
CN106419874A (en) * | 2016-11-04 | 2017-02-22 | 中央军委后勤保障部军需装备研究所 | Wearable physiology and environment monitoring system and method based on fabric electrode |
CN106570333A (en) * | 2016-11-09 | 2017-04-19 | 北京小米移动软件有限公司 | Comfort level determining method and apparatus |
CN106895881A (en) * | 2017-03-30 | 2017-06-27 | 广东欧珀移动通信有限公司 | Indoor air chemical pollution method and mobile terminal |
CN107192572A (en) * | 2017-07-11 | 2017-09-22 | 海信科龙电器股份有限公司 | Air conditioner hot comfort Performance Test System and its method of testing |
CN108036480A (en) * | 2017-12-06 | 2018-05-15 | 成都猴子软件有限公司 | Haze system based on technology of Internet of things |
CN108061360A (en) * | 2017-12-06 | 2018-05-22 | 成都猴子软件有限公司 | Be conducive to family's control method with fresh air |
CN108492044A (en) * | 2018-04-01 | 2018-09-04 | 安徽大学江淮学院 | Indoor comfort degree overall evaluation system based on artificial nerve network model and method |
CN109297534A (en) * | 2018-09-21 | 2019-02-01 | 苏州数言信息技术有限公司 | For evaluating the environmental parameter Weight Determination and system of indoor environmental quality |
CN110197186A (en) * | 2019-06-03 | 2019-09-03 | 清华大学 | A kind of illumination comfort level measurement method and system based on PPG |
CN107256341B (en) * | 2017-05-12 | 2020-10-09 | 四川省绵阳太古软件有限公司 | Ecological environment health quality assessment method |
CN113435739A (en) * | 2021-06-24 | 2021-09-24 | 哈尔滨工业大学 | Long-term indoor environment quality evaluation method and evaluation system based on environment parameter probability density function |
CN117575424A (en) * | 2024-01-16 | 2024-02-20 | 山东科技大学 | Underground environment comfort evaluation method for mine |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08122108A (en) * | 1994-10-21 | 1996-05-17 | Takenaka Komuten Co Ltd | System for measuring and evaluating indoor environment |
CN102680025A (en) * | 2012-06-06 | 2012-09-19 | 安徽农业大学 | Indoor thermal comfort evaluation system |
CN203643427U (en) * | 2013-11-22 | 2014-06-11 | 西安联控电气有限责任公司 | Indoor air quality comprehensive-detection system |
-
2016
- 2016-03-04 CN CN201610125058.8A patent/CN105698861A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08122108A (en) * | 1994-10-21 | 1996-05-17 | Takenaka Komuten Co Ltd | System for measuring and evaluating indoor environment |
CN102680025A (en) * | 2012-06-06 | 2012-09-19 | 安徽农业大学 | Indoor thermal comfort evaluation system |
CN203643427U (en) * | 2013-11-22 | 2014-06-11 | 西安联控电气有限责任公司 | Indoor air quality comprehensive-detection system |
Non-Patent Citations (1)
Title |
---|
叶廷东等: "基于物联网的室内微环境智能监测系统", 《自动化与信息工程》 * |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106419874A (en) * | 2016-11-04 | 2017-02-22 | 中央军委后勤保障部军需装备研究所 | Wearable physiology and environment monitoring system and method based on fabric electrode |
CN106419874B (en) * | 2016-11-04 | 2019-12-24 | 中央军委后勤保障部军需装备研究所 | Wearable physiological and environmental monitoring system and method based on fabric electrode |
CN106570333A (en) * | 2016-11-09 | 2017-04-19 | 北京小米移动软件有限公司 | Comfort level determining method and apparatus |
CN106570333B (en) * | 2016-11-09 | 2019-09-20 | 北京小米移动软件有限公司 | Comfort level rank determines method and device |
CN106371377A (en) * | 2016-11-21 | 2017-02-01 | 上海电机学院 | Intelligent detection device for internal environment quality |
CN106895881B (en) * | 2017-03-30 | 2019-07-16 | Oppo广东移动通信有限公司 | Indoor air chemical pollution method and mobile terminal |
CN106895881A (en) * | 2017-03-30 | 2017-06-27 | 广东欧珀移动通信有限公司 | Indoor air chemical pollution method and mobile terminal |
CN107256341B (en) * | 2017-05-12 | 2020-10-09 | 四川省绵阳太古软件有限公司 | Ecological environment health quality assessment method |
CN107192572A (en) * | 2017-07-11 | 2017-09-22 | 海信科龙电器股份有限公司 | Air conditioner hot comfort Performance Test System and its method of testing |
CN107192572B (en) * | 2017-07-11 | 2020-07-17 | 海信科龙电器股份有限公司 | Air conditioner thermal comfort performance test system and test method thereof |
CN108061360A (en) * | 2017-12-06 | 2018-05-22 | 成都猴子软件有限公司 | Be conducive to family's control method with fresh air |
CN108036480A (en) * | 2017-12-06 | 2018-05-15 | 成都猴子软件有限公司 | Haze system based on technology of Internet of things |
CN108492044A (en) * | 2018-04-01 | 2018-09-04 | 安徽大学江淮学院 | Indoor comfort degree overall evaluation system based on artificial nerve network model and method |
CN109297534A (en) * | 2018-09-21 | 2019-02-01 | 苏州数言信息技术有限公司 | For evaluating the environmental parameter Weight Determination and system of indoor environmental quality |
CN110197186A (en) * | 2019-06-03 | 2019-09-03 | 清华大学 | A kind of illumination comfort level measurement method and system based on PPG |
CN110197186B (en) * | 2019-06-03 | 2022-03-11 | 清华大学 | PPG-based illumination comfort level measurement method and system |
CN113435739A (en) * | 2021-06-24 | 2021-09-24 | 哈尔滨工业大学 | Long-term indoor environment quality evaluation method and evaluation system based on environment parameter probability density function |
CN117575424A (en) * | 2024-01-16 | 2024-02-20 | 山东科技大学 | Underground environment comfort evaluation method for mine |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105698861A (en) | Indoor environment comfort level evaluation method | |
CN104374053B (en) | Intelligent control method, device and system | |
CN104490371B (en) | A kind of thermal comfort detection method based on human body physiological parameter | |
CN107599783A (en) | A kind of environment inside car management system and its control method | |
CN105606499B (en) | Suspended particulate matter mass concentration real-time detection device, and measuring method | |
WO2020151732A1 (en) | Non-invasive ai sensing method for human thermal comfort | |
Brik et al. | An IoT-based deep learning approach to analyse indoor thermal comfort of disabled people | |
CN109784778A (en) | A kind of Electric Power Network Planning fuzzy synthetic appraisement method based on combination weights | |
CN104748305B (en) | The recognition methods of the on off state of air-conditioning and system and evaluation method and system | |
CN107480698A (en) | Method of quality control based on multiple monitoring indexes | |
CN108090515B (en) | Data fusion-based environment grade evaluation method | |
Choi et al. | Vision-based estimation of clothing insulation for building control: A case study of residential buildings | |
CN108647642A (en) | Multisensor Crack Damage error comprehensive diagnosis method based on fuzzy Fusion | |
CN112613232B (en) | Indoor human body thermal comfort prediction and evaluation method under winter heating condition | |
CN106096246B (en) | Aerosol optical depth method of estimation based on PM2.5 and PM10 | |
CN105488352B (en) | Concrete-bridge rigidity Reliability assessment method based on Long-term Deflection Monitoring Data | |
Rastogi et al. | AQCI: an IoT based air quality and thermal comfort model using fuzzy inference | |
CN206223233U (en) | A kind of experimental system for simulating for large-scale cabin environment Comfort Evaluation | |
CN116524674A (en) | Intelligent power distribution room fire early monitoring method and system based on multi-source data fusion | |
CN110298409A (en) | Multi-source data fusion method towards electric power wearable device | |
CN110033172A (en) | A kind of efficiency various dimensions evaluation method, apparatus and system | |
CN109657967A (en) | A kind of confirmation method and system of Transmission Expansion Planning in Electric evaluating indexesto scheme weight | |
CN115907204A (en) | Forest transpiration water consumption prediction method for optimizing BP neural network by sparrow search algorithm | |
Bi et al. | A fault diagnosis algorithm for wind turbine blades based on bp neural network | |
CN112613231B (en) | Track training data perturbation mechanism with balanced privacy in machine learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160622 |
|
RJ01 | Rejection of invention patent application after publication |