CN112308140A - Indoor environment quality monitoring method and terminal - Google Patents
Indoor environment quality monitoring method and terminal Download PDFInfo
- Publication number
- CN112308140A CN112308140A CN202011188082.9A CN202011188082A CN112308140A CN 112308140 A CN112308140 A CN 112308140A CN 202011188082 A CN202011188082 A CN 202011188082A CN 112308140 A CN112308140 A CN 112308140A
- Authority
- CN
- China
- Prior art keywords
- data
- indoor environment
- monitoring
- time
- satisfaction
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004364 calculation method Methods 0.000 claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 8
- 238000013528 artificial neural network Methods 0.000 claims abstract description 6
- 230000008569 process Effects 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims abstract description 4
- 230000007613 environmental effect Effects 0.000 claims description 11
- WSFSSNUMVMOOMR-UHFFFAOYSA-N Formaldehyde Chemical compound O=C WSFSSNUMVMOOMR-UHFFFAOYSA-N 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 8
- 238000005286 illumination Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 238000012806 monitoring device Methods 0.000 claims description 2
- 238000004590 computer program Methods 0.000 claims 1
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 8
- 230000001419 dependent effect Effects 0.000 description 5
- 239000003344 environmental pollutant Substances 0.000 description 5
- 229910002092 carbon dioxide Inorganic materials 0.000 description 4
- 239000001569 carbon dioxide Substances 0.000 description 4
- 238000012821 model calculation Methods 0.000 description 4
- 231100000719 pollutant Toxicity 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000001276 controlling effect Effects 0.000 description 3
- 238000009423 ventilation Methods 0.000 description 3
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 229910002091 carbon monoxide Inorganic materials 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 208000005623 Carcinogenesis Diseases 0.000 description 1
- 206010010071 Coma Diseases 0.000 description 1
- 238000001358 Pearson's chi-squared test Methods 0.000 description 1
- -1 TVOC Chemical compound 0.000 description 1
- 208000031320 Teratogenesis Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036952 cancer formation Effects 0.000 description 1
- 231100000504 carcinogenesis Toxicity 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000010791 domestic waste Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Remote Sensing (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The indoor environment monitoring method includes the steps of acquiring indoor environment real-time data, inputting the acquired indoor environment real-time data into a trained indoor environment monitoring model, and judging and disposing according to the calculation output of the indoor environment monitoring model. In the indoor environment model training process, the satisfaction degree data of personnel in the indoor environment to the environment is collected, the satisfaction degree data is matched with the indoor environment data, and an indoor environment monitoring model is established by adopting an artificial neural network algorithm according to the environment data and the satisfaction degree data.
Description
Technical Field
The invention belongs to the technical field of intelligent buildings, and particularly relates to an indoor environment quality monitoring method and a terminal.
Background
In order to solve the problem of detecting and controlling the quality of indoor environment, it is generally considered that indoor environmental pollutants mainly originate from four aspects, including: outdoor atmosphere and geological environment pollution, indoor building decoration materials and furniture release pollution, pollution generated by cooking and combustion, and pollution generated by human metabolism and volatilization of various domestic wastes. Pure natural ventilation has not been able to meet the demands of modern building environment and energy-saving control, both from the point of view of outdoor pollution isolation and from the point of view of building energy-saving level enhancement. Active monitoring and control of indoor environmental quality has become a standard configuration for modern smart buildings.
Disclosure of Invention
In one embodiment of the present invention, a method for monitoring an indoor environment,
the acquired real-time data of the indoor environment is input into a trained indoor environment monitoring model,
and judging and disposing according to the calculation output of the indoor environment monitoring model.
Collecting environment satisfaction data of people in the indoor environment during the indoor environment model training process,
matching the satisfaction data with indoor environment data,
and establishing an indoor environment monitoring model by adopting an artificial neural network algorithm according to the environment data and the satisfaction data.
The invention is different from the traditional indoor environment monitoring method and mainly comprises the following steps:
the method is not limited by the software and hardware composition and the data collection method of the quantity of questionnaire questions, so that the rigid investment of the software and the hardware is avoided as much as possible, and the user experience is improved;
the data correction method can actively deal with the problems of hardware errors and data quality, and the accuracy of the data is improved;
and thirdly, irrelevant independent variables are eliminated through a verification mode, and a calculation method capable of dynamically adjusting (independent variables, control logic and the like) is provided.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
fig. 1 is a flowchart of an indoor environment quality monitoring method according to one embodiment of the present invention.
FIG. 2 is an example of a satisfaction and regulatory profile questionnaire in accordance with one embodiment of the present invention.
Fig. 3 is a diagram of an example of an indoor environment quality monitoring model according to one embodiment of the invention.
Detailed Description
Due to the different time course and level of the harm of different pollutants to human bodies, for example, carbon monoxide (CO) can cause toxic coma and even death of people in a short time; the increase of the concentration of carbon dioxide (CO2) only causes the person to be drowsy, and the efficiency is low; although the pollutants such as formaldehyde and TVOC have little influence on human bodies in a short time, the pollutants can cause serious harm such as teratogenesis and carcinogenesis after long-term contact. Therefore, the control of indoor environment quality can make corresponding measures according to different pollutants.
Along with the continuous improvement of the quality of life and health consciousness of people, the concept of monitoring the indoor environment quality is further extended, objective data are monitored, the subjective satisfaction level of indoor personnel is more emphasized, even parameters such as the illumination level and the like which are greatly influenced by the outdoor natural environment, parameters such as the wind speed and the like which are greatly influenced by the building space, parameters such as privacy and the like which are greatly influenced by furniture arrangement, parameters such as the opening and closing state of doors and windows and the like which are greatly influenced by the behavior of the indoor personnel, and parameters such as the sitting posture of personnel and the like which are influenced by subconscious are all brought into the plate block for monitoring the satisfaction degree, and the physical and mental requirements of the indoor personnel are expected to be met or dynamically met through scientific monitoring and control.
At present, the solution for monitoring and controlling the indoor environment quality is still in a relatively 'original' state in the practice of intelligent buildings, and the existing intelligent buildings still adopt the simplest monitoring and controlling logic. For example, according to the comfort standard, a range is set for the temperature value, the temperature is reduced when the monitoring value is too high, the temperature is increased when the monitoring value is not high, and the cross action between the control logic connection factors cannot be considered, and the comprehensive satisfaction degree is not increased.
Although the logic of comprehensive monitoring control is also proposed, effective popularization of the logic is rarely seen on newly-built intelligent buildings, application can only be seen on specific demonstration buildings, and the reason for detailed analysis is still objective limitations of software and hardware of the existing logic, wherein the limitations comprise:
1) require a specific hardware composition;
2) the error of the hardware is not actively adjusted;
3) require having a particular complex software module;
4) complete data of questionnaires asking for multiple questions;
5) the data quality problem existing in engineering practice is not considered;
6) the practicability of obtaining the indoor personnel space environment information is not strong;
7) the personnel satisfaction investigation content and the digital logic thereof are not shown;
8) all data are involved in calculation, data processing is rigid, and effectiveness of conclusions is questioned.
According to one or more embodiments, as shown in fig. 1, a method for monitoring indoor environment quality is provided by a one-stop method for dynamically acquiring, processing and analyzing indoor environment data and questionnaire satisfaction data, and mainly includes the following steps:
the real-time data of the indoor environment is acquired,
inputting the acquired real-time data of the indoor environment into a trained indoor environment monitoring model,
and judging and disposing according to the calculation output of the indoor environment monitoring model.
Wherein, in the indoor environment model training process, the satisfaction degree data of the personnel in the indoor environment to the environment is collected,
matching the satisfaction data with indoor environment data,
and establishing an indoor environment monitoring model by adopting an artificial neural network algorithm according to the environment data and the satisfaction data. Before acquiring indoor environment data, error correction is carried out on indoor environment terminal monitoring equipment.
The following steps are respectively described in detail, wherein A represents the content of the indoor environment data part, B represents the content of the satisfaction questionnaire part, and C represents the content of the environment and satisfaction data comprehensive processing calculation model part.
A1) Error correction of indoor environment end monitoring equipment:
(1) the equipment is centralized in a space to monitor and upload data to a cloud platform: for air quality monitoring equipment (PM2.5, PM10, CO2, TVOC, formaldehyde and the like), hot and humid environment monitoring equipment (temperature and humidity) and noise monitoring equipment, a plurality of equipment to be subjected to error correction are displayed at the same plane height within a certain range, objective values are ensured to be equal, and monitoring value comparison is carried out. In addition, for the illumination monitoring device, vertical illumination monitoring parallel to the window is arranged at a height of 1.5m from the window, so that light uniformity is ensured.
(2) The above apparatus was monitored for 72 hours to form data sets at 1 minute intervals, and the data sets were obtained using the last 48 hours.
(3) The data quality corrected data set takes the median of all the device data at each time as the environmental data reference value at the time, and forms reference data. And randomly drawing equal data in the value-by-value section of the reference data to form data samples with equal data quantity in the value-by-value section. For example, 50 data samples of equal data volume for each temperature zone are randomly drawn between 22-22.5 ℃ of the temperature reference data and so on. At each time point, taking the median of all the device data asThe environmental data reference value at that point in time. Dividing the reference value into 10 intervals from small to large, taking 50 samples in each interval, forming 500 data samples, wherein the data of the ith equipment in the jth sample is xijThe reference value of the jth sample is yj。
(4) Calculating a linear correlation coefficient r of each device data xi and the reference data yi in the data sample, and assuming that P is less than 0.001 based on zero, the linear correlation is established, and at the moment, the intercept b is y (mean value) -rx (mean value); if P is more than or equal to 0.001, whether the equipment quality is qualified or not is considered. Among them are the following formulas:
wherein i is more than or equal to 1 and less than or equal to n, n is the number of equipment,
calculating the linear correlation coefficient r of the ith equipment data and the reference value according to the formulaiAnd intercept bi. When r is less than or equal to 0.96, r is more than or equal to 1.04, or b exceeds the error range of equipment indication, whether the equipment quality is qualified or not is considered.
A2) Data quality correction of raw data:
(1) the data uploaded to the cloud comprises monitoring point numbers (or number information added after the cloud is uploaded), time, parameters, data and equipment information.
(2) Setting a time elimination scheme, presetting a data elimination scheme of a national specified holiday and a conventional non-working time period, and manually fine-tuning the scheme or adopting the air conditioner running time as a working time period scheme.
(3) And unifying the uploaded data in time. For example, compressing a packet 1 min/time into a compressed packet 10 min/time, the compression logic is: selecting data at the 10 th min to enter a compressed packet; if the data does not exist, selecting the median of the data of the front and back 2 minutes, namely selecting the median of 4 data at 8 th, 9 th, 11 th and 12 th min as the final data of 10 th min to enter a compression packet; if no 5 data exist, the data breakpoint marked with the time value enters the compressed data packet.
(4) Processing data breakpoints: for a single or continuous two breakpoints, directly using adjacent point data as the point data; for three or more consecutive breakpoint cases, the data breakpoints are reserved.
(5) Setting an abnormal value threshold range (for example, setting the abnormal value threshold of the CO2 concentration to 390-2000ppm), when the data exceeds the threshold, firstly judging whether the values of the front and back time points are also abnormal, if so, not modifying; if the values of the front and rear time points are normal, the point value is the average value of the front and rear values. A3) Extraction of corrected environmental data: and extracting the corrected environment data according to the monitoring point number and the time range.
B1) Setting spatial information of the two-dimensional code and acquiring personal identity:
(1) the questionnaire link is set as a WeChat applet or a webpage and needs to be accessed through an account number and a password. The account number needs to be registered by WeChat or a mobile phone number, and the answering persons entering the same account number are the same person by default.
(2) The administrator can set the spatial information corresponding to the two-dimensional code by scanning the two-dimensional code based on different entries, including: monitoring point serial numbers corresponding to the two-dimensional codes, space layer height, space types, space areas, the number of people in the space, window-wall ratio, window opening orientation, distance from the window, whether the window is over against the air outlet and the like.
B2) Setup of easy satisfaction questionnaire:
(1) the satisfaction questionnaire is divided into main questions and expected regulation and control means, all questions are not necessarily answered to check the questions, and the pages are submitted by clicking.
(2) The main problems are as follows: environments that make you feel uncomfortable are: a light environment; (ii) temperature; humidity; air quality; an acoustic environment. As shown in fig. 2.
(3) The desired control measures: the specific regulation and control means comprises: natural ventilation is increased; natural ventilation is reduced; the sun shading area is reduced; the sun shading area is increased; heating; cooling; dehumidifying; humidifying; increasing the fresh air quantity; reducing the wind speed; and the noise is reduced.
B3) The method for digitizing questionnaires and spatial information comprises the following steps: and unifying questionnaire information and space information by monitoring point numbers. The two classification variables are calculated by 0 and 1; continuous variables are directly brought into the model calculation with (z-core normalized) values.
C1) Matching environmental data and questionnaire data:
(1) in the continuous variables, three continuous variables of the terminal monitoring temperature (t), the humidity (h) and the illumination (l) are respectively added with the continuous variables by square values, namely t and t are formed2、h、h2、l、l2These six continuous variables.
(2) The questionnaire/spatial data and environmental data are consolidated with the monitoring point number and time. And searching the nearest non-breakpoint environment data within 15min intervals before and after the submission time of the questionnaire, and if the non-breakpoint environment data does not exist, not participating in model calculation by the questionnaire.
C2) The factors are arguments that may be introduced into the calculation because a check is required to determine whether or not to introduce into the calculation, and are in part not objective physical data such as the square of temperature, and are therefore called factors. The method for verifying the correlation of each factor and the satisfaction degree data comprises the following steps:
(1) the judgment of the environmental satisfaction degree and the judgment of the specific regulation and control means are divided into two stages: first, objective data (independent variables) -questionnaire major questions (dependent variables); second, objective data and questionnaire main questions (independent variables) -questionnaire control means (dependent variables).
(2) The correlation of all independent and dependent variables at both stages was then examined based on matched data samples (sample size > 50).
(3) And when the independent variable is a continuous variable and the dependent variable is a binary variable, carrying out Mann-WhitneyU test on the binary variable, and if the P is less than 0.05, the continuous independent variable participates in model calculation.
(4) And when the independent variable and the dependent variable are both binary classification variables, performing Pearson chi-square test, and if P is less than 0.05, the independent variable participates in model calculation.
C3) Establishing a calculation model by using an artificial neural network algorithm:
(1) and arranging 1 layer of middle layers, and using a sigmod function in the middle layer and the output layer. The number of nodes in the middle layer can be set between 10 and 20, and when the questions in the questionnaire are checked, the questionnaire is used as an output layer. Intermediate and output layers calculated with a sigmod function. As shown in fig. 3.
(2) And calculating the weight by adopting an artificial neural network algorithm to obtain a model.
(3) And randomly extracting 30% of test data sets in the calculation data sets, and if the effectiveness of the model in the test data sets is lower than 65%, the model is invalid and the number of middle-layer nodes needs to be modified for calculation again.
(4) An independent model for each tick option of the questionnaire is obtained.
C4) Analysis after calculation:
(1) according to the level of the sample size (from high to low) of the building-floor-space-two-dimensional code, when the sample size of a hook option (hereinafter referred to as a layer hook) at a lower level is more than 10, the layer hook independent calculation model can be directly calculated and generated. If no valid model can be generated, the calculation is performed again when the number of hook samples of the layer is increased by 10.
(2) When the low-level hook independent calculation model is generated, then the higher-level hook calculation dataset excludes that portion. For example, the L floor includes X, Y, Z monitoring points, and if the "humidification" sample amount of the Z monitoring point is greater than 10, an independent "humidification" model of the Z monitoring point is generated, and at this time, the "humidification" data set of the L floor excludes the Z monitoring point data and is calculated by adding only X, Y monitoring point data.
(3) If a certain regulating means (such as temperature rise) covers a plurality of monitoring points, the monitoring points above 1/3 are required to display unsatisfactory temperature, the temperature rise is required, or the satisfaction level of the monitoring points above 2/3 is increased.
(4) And after the layer hook model is obtained, when the new sample amount is added, the model test is carried out every 10 cases, and if the effectiveness is lower than 65%, the new and old sample superposition is used as the overall sample recalculation model.
(5) And setting an alarm value according to the historical working time temperature, and alarming when the monitored temperature exceeds the alarm value.
The embodiment of the invention has the beneficial effects that:
firstly, the method acquires satisfaction data including spatial information through a questionnaire information collection scheme which is easy to practice;
processing the original data into data capable of being directly calculated through active correction logic;
and thirdly, irrelevant independent variables are eliminated by checking the relevance among the data, and dynamic control logic can be formed by calculating the change of the dynamic attention key independent variable combination and influencing individual special independent variables.
The invention provides a one-stop method for the whole process of dynamically acquiring, processing and analyzing the indoor environment data and the questionnaire satisfaction data, can meet the dynamic analysis of the indoor environment and the satisfaction of most buildings, effectively judges the standard reaching situation of the indoor environment and the satisfaction of the personnel, and provides decision logic for regulation and control actions. Compared with the traditional calculation method, the method has the advantages that the correction logic and algorithm intelligence of hardware and original data are introduced, the model can be dynamically updated, and the analysis result is more accurate. Compared with the traditional test method, the method has the advantages of good user experience and no excessive rigid software and hardware investment requirements, and is suitable for the operation analysis of most intelligent buildings. According to the invention, through relatively simple hardware data input and questionnaire data acquisition, through strict control of data quality and through a dynamically-updatable model, the analysis process is more intelligent and efficient. According to the data acquisition, processing and analysis method, the influence factors are determined through comprehensive analysis of indoor environment parameters, spatial data, user satisfaction data and the like, a dynamic satisfaction model and regulation and control logic are formed, and the prepositive problem of most building indoor environment regulation and control can be effectively solved.
It should be understood that, in the embodiment of the present invention, the term "and/or" is only one kind of association relation describing an associated object, and means that three kinds of relations may exist. For example, a and/or B, may represent: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. A method for monitoring indoor environment is characterized in that,
the real-time data of the indoor environment is acquired,
inputting the acquired real-time data of the indoor environment into a trained indoor environment monitoring model,
and judging and disposing according to the calculation output of the indoor environment monitoring model.
2. The indoor environment monitoring method according to claim 1, wherein in the indoor environment model training process, data on satisfaction of a person with an environment within an indoor environment is collected,
matching the satisfaction data with indoor environment data,
and establishing an indoor environment monitoring model by adopting an artificial neural network algorithm according to the environment data and the satisfaction data.
3. The indoor environment monitoring method of claim 1, wherein before the indoor environment data is acquired, the indoor environment end monitoring device is error corrected, the method comprising,
uploading data of monitoring equipment in the same space to a cloud platform, arranging a plurality of equipment to be subjected to error correction at the same height for air quality monitoring equipment related to PM2.5, PM10, CO2, TVOC and formaldehyde parameters, thermal and humid environment monitoring equipment related to temperature and humidity and noise monitoring equipment, arranging illumination monitoring equipment to be subjected to vertical illumination monitoring parallel to a window,
acquiring data of the monitoring equipment at regular time to obtain a data set,
using the median in the data set as the reference value of the environmental data to form reference data, randomly extracting equal data in each value section of the reference data to form data samples with equal data quantity in each value section,
calculating a linear correlation coefficient r of each device data xi and the reference data yi in the data sample, and assuming that P is less than 0.001 based on zero, wherein the linear correlation is established, and the intercept b is y (mean) -rx (mean); if P is more than or equal to 0.001, whether the equipment quality is qualified or not is considered.
4. The indoor environment monitoring method according to claim 3, wherein the step of correcting the data uploaded to the cloud platform includes:
the data uploaded to the cloud platform comprises monitoring point numbers, time, parameters, data and equipment information;
setting a time elimination scheme, including presetting a national specified holiday and data elimination of a conventional non-working time period, or manually fine-tuning the time, or adopting the air conditioner running time as a working time period;
processing the break points of the uploaded data, and directly using adjacent point data as the point data for a single break point or two continuous break points; for the conditions of three or more continuous breakpoints, the breakpoints are reserved as data breakpoints;
setting a threshold range of an abnormal value in the data, when the data exceeds the threshold, firstly judging whether the numerical value of the previous and next time points is the abnormal value, and if so, not modifying; if the values of the front and rear time points are normal, the point value is the average value of the front and rear values.
5. The indoor environment monitoring method of claim 2, wherein the method of matching satisfaction data with indoor environment data comprises,
for continuous variables in the environmental data, three continuous variables of the terminal monitoring temperature t, the humidity h and the illumination l are respectively added with the continuous variables by square values, namely t and t are formed2、h、h2、l、l2These six continuous variables;
and unifying the spatial data and the environmental data of the satisfaction data according to the environment monitoring point number and the time, searching the nearest non-breakpoint environmental data in the time interval before and after the satisfaction data, and if the satisfaction data does not exist, not adopting the satisfaction data.
6. An indoor environment monitoring terminal is characterized in that the terminal comprises a memory; and
a processor coupled to the memory, the processor configured to execute instructions stored in the memory, the processor to:
the real-time data of the indoor environment is acquired,
inputting the acquired real-time data of the indoor environment into a trained indoor environment monitoring model,
and judging and disposing according to the calculation output of the indoor environment monitoring model.
7. The indoor environment monitoring terminal according to claim 6, wherein the indoor environment monitoring model is provided on a server of a cloud platform.
8. A storage medium on which a computer program is stored which, when executed by a processor, carries out the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011188082.9A CN112308140A (en) | 2020-10-30 | 2020-10-30 | Indoor environment quality monitoring method and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011188082.9A CN112308140A (en) | 2020-10-30 | 2020-10-30 | Indoor environment quality monitoring method and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112308140A true CN112308140A (en) | 2021-02-02 |
Family
ID=74332624
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011188082.9A Pending CN112308140A (en) | 2020-10-30 | 2020-10-30 | Indoor environment quality monitoring method and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112308140A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112966448A (en) * | 2021-03-25 | 2021-06-15 | 上海市建筑科学研究院有限公司 | Indoor environment satisfaction degree acquisition and analysis method and device |
| CN113011035A (en) * | 2021-03-25 | 2021-06-22 | 上海市建筑科学研究院有限公司 | Building indoor environment satisfaction degree prediction model and method fusing spatial attributes |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102563808A (en) * | 2012-01-11 | 2012-07-11 | 华南理工大学 | Automatic control method of indoor environment comfort level |
| CN103398451A (en) * | 2013-07-12 | 2013-11-20 | 清华大学 | Multi-dimensional indoor environment controlling method and system based on learning of user behaviors |
| CN103984305A (en) * | 2014-05-06 | 2014-08-13 | 国网吉林省电力有限公司 | Method for evaluating clock state of power grid automation equipment based on data statistic analysis |
| CN104317268A (en) * | 2014-10-30 | 2015-01-28 | 林波荣 | Architectural indoor environment monitoring, feedback and control system and method based on group satisfaction degree customization and energy conservation |
| CN109164707A (en) * | 2018-09-28 | 2019-01-08 | 苏州市建筑科学研究院集团股份有限公司 | A kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm |
| CN110009245A (en) * | 2019-04-12 | 2019-07-12 | 阳江职业技术学院 | Indoor air quality prediction technique, device and electronic equipment neural network based |
| KR102018182B1 (en) * | 2018-03-15 | 2019-10-21 | 박지현 | Indoor environmental quality monitoring sensor device to define comfort index associated with energy efficiency |
| CN110555524A (en) * | 2019-07-24 | 2019-12-10 | 特斯联（北京）科技有限公司 | training sample data acquisition method and device based on indoor environment monitoring |
| CN111122775A (en) * | 2019-12-10 | 2020-05-08 | 北京蛙鸣华清环保科技有限公司 | Pollution concentration monitoring equipment-oriented segmentation data calibration method and system |
| KR20200059796A (en) * | 2018-11-22 | 2020-05-29 | 제주대학교 산학협력단 | Control system based on learning of control parameter and method thereof |
-
2020
- 2020-10-30 CN CN202011188082.9A patent/CN112308140A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102563808A (en) * | 2012-01-11 | 2012-07-11 | 华南理工大学 | Automatic control method of indoor environment comfort level |
| CN103398451A (en) * | 2013-07-12 | 2013-11-20 | 清华大学 | Multi-dimensional indoor environment controlling method and system based on learning of user behaviors |
| CN103984305A (en) * | 2014-05-06 | 2014-08-13 | 国网吉林省电力有限公司 | Method for evaluating clock state of power grid automation equipment based on data statistic analysis |
| CN104317268A (en) * | 2014-10-30 | 2015-01-28 | 林波荣 | Architectural indoor environment monitoring, feedback and control system and method based on group satisfaction degree customization and energy conservation |
| KR102018182B1 (en) * | 2018-03-15 | 2019-10-21 | 박지현 | Indoor environmental quality monitoring sensor device to define comfort index associated with energy efficiency |
| CN109164707A (en) * | 2018-09-28 | 2019-01-08 | 苏州市建筑科学研究院集团股份有限公司 | A kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm |
| KR20200059796A (en) * | 2018-11-22 | 2020-05-29 | 제주대학교 산학협력단 | Control system based on learning of control parameter and method thereof |
| CN110009245A (en) * | 2019-04-12 | 2019-07-12 | 阳江职业技术学院 | Indoor air quality prediction technique, device and electronic equipment neural network based |
| CN110555524A (en) * | 2019-07-24 | 2019-12-10 | 特斯联（北京）科技有限公司 | training sample data acquisition method and device based on indoor environment monitoring |
| CN111122775A (en) * | 2019-12-10 | 2020-05-08 | 北京蛙鸣华清环保科技有限公司 | Pollution concentration monitoring equipment-oriented segmentation data calibration method and system |
Non-Patent Citations (4)
| Title |
|---|
| 于竞宇;於蓉;张琦;张航;孔泉;: "基于机器学习的养老机构室内环境质量满意度评价模型", 西安建筑科技大学学报(自然科学版), no. 04, 28 August 2020 (2020-08-28) * |
| 卓金武，王鸿钧: "MATLAB数学建模方法与实践（第3版）", 31 July 2018, 北京航空航天大学出版社, pages: 28 - 29 * |
| 张亚楠;: "基于模型预测的教室环境品质智能控制方法的研究", 工业控制计算机, no. 09, 25 September 2017 (2017-09-25) * |
| 张寒;李晓莎;殷喜喆;郭培贤;梁欣;: "基于深度学习的室内环境检测方法的研究", 电子制作, no. 09, 1 May 2020 (2020-05-01) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112966448A (en) * | 2021-03-25 | 2021-06-15 | 上海市建筑科学研究院有限公司 | Indoor environment satisfaction degree acquisition and analysis method and device |
| CN113011035A (en) * | 2021-03-25 | 2021-06-22 | 上海市建筑科学研究院有限公司 | Building indoor environment satisfaction degree prediction model and method fusing spatial attributes |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1866575B1 (en) | Method and system for controlling a climate in a building | |
| CN112308140A (en) | Indoor environment quality monitoring method and terminal | |
| Aizer | The gender wage gap and domestic violence | |
| Pazhoohesh et al. | A satisfaction-range approach for achieving thermal comfort level in a shared office | |
| Imagawa et al. | Field survey of the thermal comfort, quality of sleep and typical occupant behaviour in the bedrooms of Japanese houses during the hot and humid season | |
| Li et al. | A personalized HVAC control smartphone application framework for improved human health and well-being | |
| CN111443609A (en) | Laboratory environment self-adaptive adjusting method based on Internet of things | |
| Fan et al. | Research on risk scorecard of sick building syndrome based on machine learning | |
| CN111223564A (en) | Noise hearing loss prediction system based on convolutional neural network | |
| Thorve et al. | High resolution synthetic residential energy use profiles for the United States | |
| Wu et al. | Comparative analysis of indoor air quality in green office buildings of varying star levels based on the grey method | |
| CN109883016A (en) | A kind of air pleasant degree adjusting method and equipment | |
| Zhu et al. | Consideration of occupant preferences and habits during the establishment of occupant-centric buildings: a critical review | |
| CN108647817B (en) | Energy consumption load prediction method and system | |
| Kumar | Subject's thermal adaptation in different built environments: An analysis of updated metadata-base of thermal comfort data in India | |
| CN113050439A (en) | Self-learning intelligent household control method, control equipment and computer readable storage medium | |
| CN116453696A (en) | Respiratory tract disease infection risk prediction method based on personnel space-time distribution model | |
| CN116862283A (en) | Method and system for evaluating and controlling environment of aged people | |
| CN112966448A (en) | Indoor environment satisfaction degree acquisition and analysis method and device | |
| Swanson et al. | Indoor annual sunlight opportunity in domestic dwellings may predict well-being in urban residents in scotland | |
| Wei | Occupant's space heating behaviour in a simulation-intervention loop | |
| Monsberger et al. | An innovative user feedback system for sustainable buildings | |
| Wang et al. | Thermal perception and lung function: a panel study in young adults with exercise under high outdoor temperature | |
| Lu et al. | A novel AC turning on behavior model based on survival analysis | |
| CN112212481A (en) | System and method for controlling environmental comfort by deep reinforcement learning |
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 |