CN114689478B - Air quality detection device and method - Google Patents
Air quality detection device and method Download PDFInfo
- Publication number
- CN114689478B CN114689478B CN202210362248.7A CN202210362248A CN114689478B CN 114689478 B CN114689478 B CN 114689478B CN 202210362248 A CN202210362248 A CN 202210362248A CN 114689478 B CN114689478 B CN 114689478B
- Authority
- CN
- China
- Prior art keywords
- module
- air
- air quality
- concentration
- prediction
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 178
- 238000000034 method Methods 0.000 title claims abstract description 20
- 239000000809 air pollutant Substances 0.000 claims abstract description 107
- 231100001243 air pollutant Toxicity 0.000 claims abstract description 107
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 230000007613 environmental effect Effects 0.000 claims description 71
- 238000005070 sampling Methods 0.000 claims description 38
- 238000012549 training Methods 0.000 claims description 28
- 238000010801 machine learning Methods 0.000 claims description 20
- WSFSSNUMVMOOMR-UHFFFAOYSA-N Formaldehyde Chemical compound O=C WSFSSNUMVMOOMR-UHFFFAOYSA-N 0.000 claims description 9
- 239000000356 contaminant Substances 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 238000003672 processing method Methods 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 239000012855 volatile organic compound Substances 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 239000003344 environmental pollutant Substances 0.000 abstract description 8
- 231100000719 pollutant Toxicity 0.000 abstract description 8
- 238000007637 random forest analysis Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- WSFSSNUMVMOOMR-NJFSPNSNSA-N methanone Chemical compound O=[14CH2] WSFSSNUMVMOOMR-NJFSPNSNSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
- G01N33/0036—General constructional details of gas analysers, e.g. portable test equipment concerning the detector specially adapted to detect a particular component
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
- G01N33/0036—General constructional details of gas analysers, e.g. portable test equipment concerning the detector specially adapted to detect a particular component
- G01N33/0047—Organic compounds
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Combustion & Propulsion (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Dispersion Chemistry (AREA)
- Sampling And Sample Adjustment (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses an air quality detection device and a method, wherein the device comprises: an air quality detection module; a moving module; a lifting module; a control module; the prediction module is used for acquiring a concentration distribution model of various air pollutants in the indoor space according to the air quality parameter detection result obtained by the air quality detection module and obtaining the average concentration of various air pollutants in the indoor space; and a display module. The air quality detection device provided by the invention can move indoors independently, so that air quality detection is carried out on multiple indoor points, and the detection precision is improved; in the invention, the concentration of a small amount of points is collected, then the concentration of a point with high reliability and enough amount can be predicted, the pollutant concentration distribution of the whole indoor space is described through a plurality of points, and the pollutant concentration result is obtained through calculation, so that the method has higher precision, higher efficiency and better practicability.
Description
Technical Field
The invention relates to the technical field of environment detection, in particular to an air quality detection device and method.
Background
Since many air pollutants, such as PM2.5, formaldehyde, organic volatile compounds (VOCs) and the like, exist in indoor spaces (such as houses, offices, markets and the like) due to the presence of decoration materials, furniture and the like containing pollutants and the pollution of outside air, the detection of the content of the air pollutants in the indoor spaces before the residents live (particularly in newly decorated rooms) or during the live can help the residents judge whether the indoor environments are suitable for living, and the detection has important significance for ensuring the physical health of the residents.
At present, most of detection devices for indoor space air pollutants do not have an automatic moving function and need to be manually moved to each detection point for detection, for example, an air detector disclosed in patent CN110286201B, which has the defect of inconvenient use. Based on this, patent CN113552817A discloses a movable air detection device, a detection method and an air detector, wherein the air detection device can automatically move to detect a plurality of areas in a value room, so that convenience can be improved; a large number of similar prior arts including this patent (such as a multi-directional air detection device for indoor air detection disclosed in patent CN 106405002B) still have at least the following defects: the precision of the detection result is not only the instrument itself, but also one of the main influencing factors is the nonuniformity of the indoor air pollutant concentration in the spatial distribution (for example, the concentration is different along the height direction, or the concentration is different at different positions on the same horizontal plane), so the precision is usually improved by using a method of measuring a plurality of points and then taking an average value; the sampling point is more, and must the precision be higher, but every point detects and all need spend certain time, if gather a large amount of points, can consume a large amount of time cost and energy consumption cost, so it is limited to improve the scheme effect of precision through increasing the sampling point alone, can't be fine satisfies adaptation actual demand.
Therefore, there is a need to provide a more reliable solution.
Disclosure of Invention
The present invention provides an air quality detection device and method, aiming at the above-mentioned deficiencies in the prior art.
In order to solve the technical problems, the invention adopts the technical scheme that: an air quality detection device comprising:
the air quality detection module is used for detecting the concentration of indoor air pollutants;
a moving module for enabling movement of the air quality detection apparatus indoors;
the lifting module is arranged on the moving module and used for realizing the movement of the air quality detection module in the vertical direction;
the control module is used for controlling the air quality detection module, the moving module and the lifting module;
the prediction module is used for acquiring a concentration distribution model of various air pollutants in the indoor space according to the air quality parameter detection result acquired by the air quality detection module and acquiring the average concentration of various air pollutants in the indoor space;
and a display module which displays at least the indoor air pollutant concentration directly detected by the air quality detection module and the air pollutant concentration distribution model and the air pollutant average concentration of each indoor space obtained by the prediction module.
Preferably, the air quality detection device further comprises a positioning module, and the positioning module is used for positioning the position of the air quality detection module in real time.
Preferably, the air quality detection device further comprises an environmental parameter detection module, wherein the environmental parameter detection module comprises an air flow rate detection unit, a temperature detection unit, a humidity detection unit and an air pressure detection unit.
Preferably, the air quality detection module includes at least a PM2.5 detection sensor, a formaldehyde detection sensor, and a Volatile Organic Compound (VOC) detection sensor.
Preferably, the air quality detection device further comprises a distance measurement module and a navigation module, wherein the distance measurement module is used for detecting the distance between the air quality detection device and the obstacle in real time, and the navigation module is used for providing auxiliary navigation for the moving module so as to realize that the air quality detection module moves indoors according to a preset track.
Preferably, the prediction module comprises a first prediction network model, a second prediction network model, a database, a model construction unit and a data calculation unit;
the processing method of the prediction module comprises the following steps:
1) Constructing a training data set;
2) Training the first prediction network model and the second prediction network model by adopting a training data set:
3) Detecting the concentration of air pollutants at a plurality of sampling points in an indoor space to be detected through the air quality detection device, wherein the sampling points are used as reference points; simultaneously, detecting the environmental parameters in the indoor space to be detected through the environmental parameter detection module, then inputting the detection data of the plurality of reference points and the environmental parameters into the prediction module, and obtaining the concentration of various air pollutants at a plurality of prediction points respectively corresponding to each reference point through prediction; each datum point corresponds to a plurality of prediction points around the spatial position of the datum point;
4) And the model building and data calculating unit builds a concentration distribution model of various air pollutants in the indoor space to be measured according to the concentrations of the various air pollutants at all the reference points and the prediction points, and calculates to obtain the average concentration of the various air pollutants.
Preferably, the first prediction network model includes an LDA (linear discrete analysis) Machine learning model, an FFM (Field-aware factory Machine) Machine learning model, and an RF (random forest) Machine learning model;
the second predictive network model is a stacked network model.
Preferably, the processing method of the prediction module includes the following steps:
1) Constructing a training data set:
1-1) collecting a plurality of unit area data in an indoor space:
1-1-1) selecting a point of the non-spatial edge area in the current indoor space as a reference point O G Detecting the reference point O by the air quality detection module G Concentration of air pollutants C G ；
1-1-2) in the current indoor space, selecting the following and at the reference point O G Corresponding 6 predicted points; at reference point O G Right above (D) and at a distance D, and is recorded as an upper predicted point O up (ii) a At reference point O G Is right below the point (D), and is marked as a lower predicted point O down (ii) a At reference point O G Right left and distance D, and marking as left predicted point O L (ii) a At reference point O G Right ofAnd the distance D is taken as a point and is marked as a right predicted point O R (ii) a At reference point O G Right ahead of and at a distance D, and is marked as a front predicted point O A (ii) a At reference point O G Right behind (D), and the distance D, and is recorded as the post-prediction point O B (ii) a Wherein the distance D is set such that all points: o is up 、O down 、O L 、O R 、O A 、O B Are all in the current indoor space;
respectively detecting O through the air quality detection module up 、O down 、O L 、O R 、O A 、O B The concentration of air pollutants at each point, denoted C in turn up 、C down 、C L 、C R 、C A 、C B ；
Detecting and recording all points through the positioning module: o is G 、O up 、O down 、O L 、O R 、O A 、O B The spatial position coordinates of (a);
each point is: o is G 、O up 、O down 、O L 、O R 、O A 、O B Spatial position coordinates of (a), air pollutant concentration at each point: c G 、C up 、C down 、C L 、C R 、C A 、C B And combining the distances D into a unit area data s;
1-1-3) collecting a plurality of unit area data s according to the steps 1-1-1) to 1-1-2);
1-1-4) detecting an environmental parameter H in the current indoor space through the environmental parameter detection module, wherein the environmental parameter H comprises a temperature T, a humidity RH, an air pressure P and an air flow velocity V, and is marked as H = (T, RH, P, V); among them, the temperature T, humidity RH, air pressure P, and air velocity V have an important influence on the distribution of indoor air pollutants (the study of influence of meteorological conditions on the distribution of pollutant concentrations "desert and oasis meteorology" 2015 phase 2 wangyanglewanglixia);
1-1-5) combining the environmental parameters H and all the acquired unit area data S to form a data set, namely a training data set S, and storing the data set in the database;
2) Training a network model:
2-1) for each air contaminant Wi, with reference point O in each unit area data s G Spatial position coordinates of (1), reference point O G Concentration C of Wi of GWi Distance D and environment parameter H as input, and each unit area data s is compared with reference point O G All corresponding predicted points: o is up 、O down 、O L 、O R 、O A 、O B Concentration C of air pollutant Wi of upWi 、C downWi 、C LWi 、C RWi 、C AWi 、C BWi For output, the three machine learning models of LDA, kNN and SVMs are trained by adopting the training data set S, and each machine learning model obtains a prediction relational expression group F of the air pollutants Wi Wi ，F Wi Comprising f1 Wi 、f2 Wi 、f3 Wi 、f4 Wi 、f5 Wi 、f6 Wi Is marked as F Wi =（f1 Wi ,f2 Wi ,f3 Wi ,f4 Wi ,f5 Wi ,f6 Wi ）；
Wherein, f1 Wi Represents: air contaminant Wi at the predicted point O up Concentration of C upWi At a reference point O G Concentration of C GWi Difference value Δ 1 therebetween Wi Is identical to O up And O G The relationship between the distance D directly above and the environmental parameter H, denoted by Δ 1 Wi =f1 Wi (D Oup-OG ,H)；
F2 Wi Represents: c downWi And C GWi Difference value Δ 2 therebetween Wi Is identical to O down And O G The relationship between the distance D directly below and the environmental parameter H is expressed as Δ 2 Wi =f2 Wi (D Odown-OG ,H)；
F3 Wi Represents: c LWi And C GWi Difference value Δ 3 therebetween Wi Is identical to O L And O G Distance D between the right and left and environmental parameter HIs expressed as Δ 3 Wi =f3 Wi (D OL-OG ,H)；
F4 Wi Represents: c RWi And C GWi Difference Δ 4 therebetween Wi Is identical to O R And O G The relationship between the distance D between the right and the left and the environmental parameter H is represented by Δ 4 Wi =f4 Wi (D OR-OG ,H)；
F5 Wi Represents: c AWi And C GWi Difference Δ 5 therebetween Wi Is identical to O A And O G The relationship between the distance D between the straight ahead and the environmental parameter H, denoted Δ 5 Wi =f5 Wi (D OA-OG ,H)；
F6 Wi Represents: c BWi And C GWi Difference Δ 6 therebetween Wi Is identical to O B And O G The relationship between the distance D between the right and the rear and the environmental parameter H, denoted by Δ 6 Wi =f6 Wi (D OB-OG ,H)；
2-2) obtaining a prediction relational expression group F by three machine learning models of LDA, kNN and SVMs respectively Wi Reference point O in each piece of cell region data s G Spatial position coordinates of (1), reference point O G Concentration C of Wi GWi Distance D and environment parameter H as input, and each unit area data s is compared with reference point O G All corresponding predicted points: o is up 、O down 、O L 、O R 、O A 、O B Concentration C of air pollutant Wi of upWi 、C downWi 、C LWi 、C RWi 、C AWi 、C BWi Training the stacked network model for output;
2-3) finishing the training of the data of each air pollutant Wi according to the steps 2-1) to 2-2) to obtain a trained first prediction network model and a trained second prediction network model;
3) Detecting the concentration of air pollutants through a plurality of sampling points of the air quality detection device in an indoor space to be detected, and taking the sampling points as reference points O G While participating in the environmentThe number detection module simultaneously detects the environmental parameters H in the indoor space to be detected, and then a plurality of reference points O G Inputting the parameters into the prediction module together with the environmental parameters H, and outputting the prediction through the second prediction network model to obtain the reference point O G The concentrations of various air pollutants at 6 corresponding prediction points respectively;
4) The model building and data calculating unit builds a concentration distribution model of various air pollutants in the indoor space to be measured according to the concentrations of various air pollutants at all the reference points and the prediction points; for each air pollutant Wi, the average value of the concentrations at all the reference points and the predicted points is taken as the average concentration of the air pollutant Wi, so as to obtain the average concentration of each air pollutant.
Preferably, the sampling points include at least 4 sampling points spaced from each other, and the 4 sampling points are not in the same horizontal plane or the same vertical plane at the same time.
The invention also provides an air quality detection method for detecting the concentration of air pollutants in an indoor space by adopting the air quality detection device, which comprises the following steps:
s1, controlling the moving module and the lifting module through the control module, moving the air quality detection device to an indoor space to be detected, and detecting the concentration of air pollutants at least 4 sampling points, wherein the 4 sampling points are not in the same horizontal plane or the same vertical plane at the same time; in the detection process, the moving module realizes the movement of the air quality detection device in the horizontal direction, and the lifting module realizes the movement of the air quality detection device in the vertical direction;
s2, the environmental parameter detection module simultaneously detects the environmental parameters in the indoor space to be detected;
s3, the prediction module receives detection results of the air quality detection module and the environmental parameter detection module, and predicts a concentration distribution model of various air pollutants in the indoor space to be detected and an average concentration of various air pollutants;
and S4, the display module displays the detection results of the air quality detection module and the environmental parameter detection module and the prediction result of the prediction module.
The beneficial effects of the invention are:
the air quality detection device provided by the invention can move indoors independently, so that air quality detection is carried out on multiple indoor points, and the detection precision is improved;
in the invention, the concentration of a small amount of points is collected, then the concentration of a sufficient amount of points with high reliability can be predicted, the pollutant concentration distribution of the whole indoor space is described through a plurality of points, and a pollutant concentration result is obtained through calculation, so that the method has higher precision, higher efficiency and better practicability;
the prediction method of the invention combines the indoor environmental factors of temperature T, humidity RH, air pressure P and air flow velocity V, and is realized by using a machine learning algorithm on the basis of a large amount of data, so that the method has higher reliability, and the prediction result is closer to the reality due to the consideration of the environmental factors which have main influence on the concentration distribution of indoor air pollutants.
Drawings
FIG. 1 is a schematic structural diagram of an air quality detecting apparatus according to the present invention;
fig. 2 is a flow chart of the air quality detection method of the present invention.
Detailed Description
The present invention is further described in detail below with reference to examples so that those skilled in the art can practice the invention with reference to the description.
It will be understood that terms such as "having," "including," and "comprising," as used herein, do not preclude the presence or addition of one or more other elements or groups thereof.
Example 1
Referring to fig. 1, an air quality detecting apparatus of the present embodiment includes:
the air quality detection module is used for detecting the concentration of indoor air pollutants;
the moving module is used for realizing the movement of the air quality detection device in a room;
the lifting module is arranged on the moving module and used for realizing the movement of the air quality detection module in the vertical direction;
the control module is used for controlling the air quality detection module, the moving module and the lifting module;
the prediction module is used for acquiring a concentration distribution model of various air pollutants in the indoor space according to the air quality parameter detection result acquired by the air quality detection module and acquiring the average concentration of various air pollutants in the indoor space;
and the display module at least displays the indoor air pollutant concentration directly detected by the air quality detection module and the air pollutant concentration distribution model and the air pollutant average concentration of each indoor space obtained by the prediction module.
In a preferred embodiment, the air quality detection device further comprises a positioning module, an environmental parameter detection module, an air quality detection module, a distance measurement module and a navigation module.
The positioning module is used for positioning the position of the air quality detection module in real time.
The environmental parameter detection module comprises an air flow rate detection unit, a temperature detection unit, a humidity detection unit and an air pressure detection unit.
The air quality detection module at least comprises a PM2.5 detection sensor, a formaldehyde detection sensor and a Volatile Organic Compound (VOC) detection sensor.
The distance measurement module is used for detecting the distance between the air quality detection device and the barrier in real time, and the navigation module is used for providing auxiliary navigation for the moving module so as to realize that the air quality detection module moves indoors according to a preset track.
In one embodiment, the air quality detection device comprises a host, the modules are arranged on the host, universal wheels are arranged at the bottom of the host, and the moving module drives the universal wheels to move so as to realize the integral movement of the air quality detection device.
The positioning module, the environmental parameter detection module, the air quality detection module, the distance measurement module, the navigation module and the like are all products which can realize corresponding functions in the prior art, and the invention is not particularly limited.
In this embodiment, the prediction module includes a first prediction network model, a second prediction network model, a database, a model construction unit, and a data calculation unit;
the processing method of the prediction module comprises the following steps:
1) Constructing a training data set;
2) Training the first prediction network model and the second prediction network model by adopting a training data set:
3) Detecting the concentration of air pollutants at a plurality of sampling points in an indoor space to be detected through an air quality detection device, wherein the sampling points are used as reference points; simultaneously, detecting the environmental parameters in the indoor space to be detected through an environmental parameter detection module, inputting the detection data of the plurality of reference points and the environmental parameters into a prediction module, and obtaining the concentration of various air pollutants at a plurality of prediction points respectively corresponding to each reference point through prediction; each reference point corresponds to a plurality of prediction points around the spatial position of the reference point;
4) And the model building and data calculating unit builds a concentration distribution model of various air pollutants in the indoor space to be measured according to the concentrations of the various air pollutants at all the reference points and the prediction points, and calculates to obtain the average concentration of the various air pollutants.
The general idea in the invention is as follows:
1. the air quality detection device can be driven to move indoors by matching the moving module with the lifting module, so that air quality detection is performed on multiple indoor points, and the detection precision is improved;
2. firstly, a small number of points are collected indoors to be used as reference points, the air pollutant concentrations at the reference points are detected, then based on the current indoor environmental parameters (factors which have large influence on the distribution of the indoor air pollutant concentrations), the air pollutant concentrations of a plurality of prediction points near each reference point are predicted through a prediction module, so that the air pollutant concentrations at a large number of prediction points with high reliability can be obtained through the detection data of the small number of points, finally, the distribution condition of the indoor air pollutant concentrations is described through the reference points and the air pollutant concentrations at the large number of prediction points, and the average concentration of the indoor air pollutants is calculated; compared with the scheme that only the detection data of 1 sampling point or the average value of the detection data of a plurality of sampling points is used as the detection result in the conventional mode, the method can predict the air pollutant concentration at a large number of prediction points which are distributed at intervals in the space according to the main influence factors of the air pollutant concentration distribution, the detection result obtained on the basis can be closer to the actual situation, the detection precision and the detection range are obviously improved, and more valuable and reliable results can be provided for the detection of the indoor air concentration.
The details are described below with reference to more specific embodiments.
In this embodiment, the first prediction network model includes an LDA (linear discrete analysis) Machine learning model, an FFM (Field-aware localization Machine) Machine learning model, and an RF (random forest) Machine learning model; the second predictive network model is a stacked network model.
The processing method of the prediction module comprises the following steps:
1) Constructing a training data set:
1-1) collecting a plurality of unit area data in an indoor space:
1-1-1) selecting a point of a non-spatial edge area in a current indoor space as a reference point O G Detecting the reference point O by an air quality detection module G Air pollutant concentration C G ；
1-1-2) in the current indoor space, selecting the following and at the reference point O G Corresponding 6 predicted points; at reference point O G Right above (D) and at a distance D, and marking as an upper predicted point O up (ii) a At reference point O G Is right below the point (D), and is marked as a lower predicted point O down (ii) a At reference point O G Right left and distance D, and marking as left predicted point O L (ii) a At reference point O G Right and left of (D) and the distance is D, and is marked as the right predicted point O R (ii) a At reference point O G Right ahead of and at a distance D, and is marked as a front predicted point O A (ii) a At reference point O G Right behind (D) and at a distance D, and recording as a rear predicted point O B (ii) a Wherein the distance D is set such that all points: o is up 、O down 、O L 、O R 、O A 、O B Are all in the current indoor space;
respectively detecting O through air quality detection modules up 、O down 、O L 、O R 、O A 、O B The concentration of air pollutants at each point, denoted C in turn up 、C down 、C L 、C R 、C A 、C B ；
All points are detected and recorded by the positioning module: o is G 、O up 、O down 、O L 、O R 、O A 、O B The spatial position coordinates of (a);
each point is: o is G 、O up 、O down 、O L 、O R 、O A 、O B Spatial position coordinates of (a), air pollutant concentration at each point: c G 、C up 、C down 、C L 、C R 、C A 、C B And combining the distance D into a unit area data s;
1-1-3) collecting a plurality of unit area data s according to the steps 1-1-1) to 1-1-2);
1-1-4) detecting an environmental parameter H in the current indoor space through an environmental parameter detection module, wherein the environmental parameter H comprises temperature T, humidity RH, air pressure P and air flow velocity V, and is marked as H = (T, RH, P, V);
1-1-5) combining the environmental parameters H and all the acquired unit area data S to form a data set, namely a training data set S, and storing the training data set S in a database;
2) Training a network model:
2-1) for each air contaminant Wi, at reference point O in each unit area data s G Spatial position coordinates of (1), reference point O G Concentration C of Wi of GWi The distance D and the environmental parameter H are used as input, and each unit area data s is compared with the reference point O G All corresponding predicted points: o is up 、O down 、O L 、O R 、O A 、O B Concentration C of air pollutant Wi of upWi 、C downWi 、C LWi 、C RWi 、C AWi 、C BWi For output, three machine learning models of LDA, kNN and SVMs are trained by adopting a training data set S, and each machine learning model obtains a prediction relational expression group F of the air pollutants Wi Wi ，F Wi Comprising f1 Wi 、f2 Wi 、f3 Wi 、f4 Wi 、f5 Wi 、f6 Wi Is marked as F Wi =（f1 Wi ,f2 Wi ,f3 Wi ,f4 Wi ,f5 Wi ,f6 Wi ）；
Wherein, f1 Wi Represents: air contaminant Wi at predicted point O up Concentration of (C) upWi At a reference point O G Concentration of C GWi Difference value Δ 1 therebetween Wi Is identical to O up And O G The relationship between the distance D directly above and the environmental parameter H is denoted by Δ 1 Wi =f1 Wi (D Oup-OG ,H)；
F2 Wi Represents: c downWi And C GWi Difference value Δ 2 therebetween Wi Is identical to O down And O G The relationship between the distance D directly below and the environmental parameter H is represented by Δ 2 Wi =f2 Wi (D Odown-OG ,H)；
F3 Wi Represents: c LWi And C GWi Difference value Δ 3 therebetween Wi Is identical to O L And O G The relationship between the distance D between the right and left and the environmental parameter H, denoted by Δ 3 Wi =f3 Wi (D OL-OG ,H)；
F4 Wi Represents: c RWi And C GWi Difference Δ 4 therebetween Wi Is identical to O R And O G The relationship between the distance D between the right and the left and the environmental parameter H is represented by Δ 4 Wi =f4 Wi (D OR-OG ,H)；
F5 Wi Represents: c AWi And C GWi Difference Δ 5 therebetween Wi Is identical to O A And O G The relationship between the distance D between the straight ahead and the environmental parameter H, denoted Δ 5 Wi =f5 Wi (D OA-OG ,H)；
F6 Wi Represents: c BWi And C GWi Difference Δ 6 therebetween Wi Is identical to O B And O G The relationship between the distance D between the right and the rear and the environmental parameter H is denoted by Δ 6 Wi =f6 Wi (D OB-OG ,H)；
2-2) a prediction relational expression group F obtained by three machine learning models of LDA, kNN and SVMs Wi Reference point O in each piece of cell region data s G Spatial position coordinates of (2), reference point O G Concentration C of Wi of GWi Distance D and environment parameter H as input, and each unit area data s is compared with reference point O G All corresponding predicted points: o is up 、O down 、O L 、O R 、O A 、O B Concentration C of air pollutant Wi of upWi 、C downWi 、C LWi 、C RWi 、C AWi 、C BWi Training the stacked network model for output;
2-3) finishing the training of the data of each air pollutant Wi according to the steps 2-1) to 2-2) to obtain a trained first prediction network model and a trained second prediction network model;
3) Detecting the concentration of air pollutants through a plurality of sampling points of an air quality detection device in an indoor space to be detected, and taking the sampling points as reference points O G Simultaneously detecting the indoor space to be detected through an environmental parameter detection moduleAnd then several reference points O G Inputting the parameters into a prediction module together with the environmental parameters H, and outputting prediction through a second prediction network model to obtain the parameters of each reference point O G The concentrations of various air pollutants at 6 corresponding prediction points respectively;
4) The model building and data calculating unit builds a concentration distribution model of various air pollutants in the indoor space to be measured according to the concentrations of various air pollutants at all the reference points and the prediction points; for each air pollutant Wi, the average value of the concentrations at all the reference points and the predicted points is taken as the average concentration of the air pollutant Wi, so that the average concentration of various air pollutants is obtained.
For example, in one embodiment, for collecting 6 reference points, 6 × 6=36 predicted points can be obtained, and the final data points can be expanded to 6+36=42, so the data volume is greatly increased, and the detection accuracy can be improved.
In some embodiments, the detection accuracy can be improved by further increasing the number of predicted points without increasing the number of reference points. Inputting the prediction result in the step 3) as a new reference point into the prediction module, and then predicting through the first prediction network model and the second prediction network model to obtain a new prediction point, so that more data can be obtained through secondary prediction. For example, in the case of detecting a location with a large indoor space, 36 predicted points obtained by the first prediction by the second prediction network model can be input, that is, can be used as new reference points, and the prediction module can obtain 36 × 6=216 new predicted points, thereby further increasing the data volume.
In other words, in this embodiment, the air pollutant concentration of a reference point is detected, and then the tested air pollutant concentrations of the reference point which is equal to the reference point in space position and is distributed at the upper, lower, left, right, front and rear 6 positions are predicted; the prediction method is realized by combining the environmental factors of indoor temperature T, humidity RH, air pressure P and air flow velocity V and utilizing a machine learning algorithm on the basis of a large amount of data, so that the reliability is high, and the prediction result is closer to the reality due to the consideration of the environmental factors which have main influence on the concentration distribution of indoor air pollutants.
The detection accuracy can be improved by acquiring a plurality of points and then averaging, but the defects are obvious: the sampling point is more, and must the precision be higher, but every point detects and all need spend certain time, if gather a large amount of points, can consume a large amount of time cost and energy consumption cost, can't adapt to actual demand. In the invention, the concentration of a small amount of points is collected, then the concentration of a sufficient amount of points with high reliability can be predicted, the pollutant concentration distribution of the whole indoor space is described through a plurality of points, and the pollutant concentration result is obtained through calculation, so that the method has higher precision, higher efficiency and better practicability.
The sampling points at least comprise 4 mutually spaced sampling points, and the 4 sampling points are not in the same horizontal plane or the same vertical plane at the same time. By enabling the sampling points to be located on the same horizontal plane or the same vertical plane at the same time, data of the sampling points at different horizontal positions and vertical positions can be introduced to serve as a prediction reference, and detection accuracy can be improved. For example, in one embodiment, the connection line including 4 sampling points may form a tetrahedral structure. In another embodiment, the connecting line comprising 6 sampling points forms a rectangular structure. It can be understood that the more sampling points, the higher the accuracy of the finally obtained detection data, but the larger the corresponding calculation amount. Generally, for a room of a general residential room, the indoor volume is not more than 40m 3 And 4-6 sampling points can meet the requirement.
Example 2
Referring to fig. 2, the present embodiment provides an air quality detecting method for detecting the concentration of air pollutants in an indoor space using the air quality detecting apparatus of embodiment 1, the method including the steps of:
s1, controlling a moving module and a lifting module through a control module, moving an air quality detection device to an indoor space to be detected, and detecting the concentration of air pollutants at least 4 sampling points, wherein the 4 sampling points are not in the same horizontal plane or the same vertical plane at the same time; in the detection process, the moving module realizes the movement of the air quality detection device in the horizontal direction, and the lifting module realizes the movement of the air quality detection device in the vertical direction;
s2, simultaneously detecting the environmental parameters in the indoor space to be detected by an environmental parameter detection module;
s3, the prediction module receives detection results of the air quality detection module and the environmental parameter detection module, and predicts a concentration distribution model of various air pollutants in the indoor space to be detected and the average concentration of various air pollutants;
and S4, the display module displays the detection results of the air quality detection module and the environmental parameter detection module and the prediction result of the prediction module.
While embodiments of the invention have been disclosed above, it is not limited to the applications listed in the description and the embodiments, which are fully applicable in all kinds of fields of application of the invention, and further modifications may readily be effected by those skilled in the art, so that the invention is not limited to the specific details without departing from the general concept defined by the claims and the scope of equivalents.
Claims (5)
1. An air quality detection device, comprising:
the air quality detection module is used for detecting the concentration of indoor air pollutants;
a moving module for enabling movement of the air quality detection apparatus indoors;
the lifting module is arranged on the moving module and used for realizing the movement of the air quality detection module in the vertical direction;
the control module is used for controlling the air quality detection module, the moving module and the lifting module;
the prediction module is used for acquiring a concentration distribution model of various air pollutants in the indoor space according to the air quality parameter detection result acquired by the air quality detection module and acquiring the average concentration of various air pollutants in the indoor space;
the display module at least displays the indoor air pollutant concentration directly detected by the air quality detection module, and the air pollutant concentration distribution model and the air pollutant average concentration of each indoor space obtained by the prediction module;
the air quality detection device also comprises a positioning module, and the positioning module is used for positioning the position of the air quality detection module in real time;
the air quality detection device also comprises an environmental parameter detection module, wherein the environmental parameter detection module comprises an air flow rate detection unit, a temperature detection unit, a humidity detection unit and an air pressure detection unit;
the prediction module comprises a first prediction network model, a second prediction network model, a database and a model construction and data calculation unit;
the processing method of the prediction module comprises the following steps:
1) Constructing a training data set;
2) Training the first prediction network model and the second prediction network model by adopting a training data set:
3) Detecting the concentration of air pollutants at a plurality of sampling points in an indoor space to be detected through the air quality detection device, wherein the sampling points are used as reference points; simultaneously, detecting the environmental parameters in the indoor space to be detected through the environmental parameter detection module, inputting the detection data of the plurality of reference points and the environmental parameters into the prediction module, and obtaining the concentration of various air pollutants at a plurality of prediction points respectively corresponding to each reference point through prediction; each datum point corresponds to a plurality of prediction points around the spatial position of the datum point;
4) The model building and data calculating unit builds a concentration distribution model of various air pollutants in the indoor space to be measured according to the concentrations of the various air pollutants at all the reference points and the prediction points, and calculates to obtain the average concentration of the various air pollutants;
the first predictive network model comprises an LDA machine learning model, an FFM machine learning model and an RF machine learning model;
the second predictive network model is a stacked network model;
the processing method of the prediction module comprises the following steps:
1) Constructing a training data set:
1-1) collecting a plurality of unit area data in an indoor space:
1-1-1) selecting a point of the non-spatial edge area in the current indoor space as a reference point O G Detecting the reference point O by the air quality detection module G Concentration of air pollutants C G ；
1-1-2) in the current indoor space, select the following and at reference point O G Corresponding 6 predicted points; at reference point O G Right above (D) and at a distance D, and is recorded as an upper predicted point O up (ii) a At reference point O G Is right below the point (D), and is marked as a lower predicted point O down (ii) a At reference point O G Right left and distance D, and marking as left predicted point O L (ii) a At reference point O G Right and left of (D) and the distance is D, and is marked as the right predicted point O R (ii) a At reference point O G Right ahead of and at a distance D, and is marked as a front predicted point O A (ii) a At reference point O G Right behind (D) and at a distance D, and recording as a rear predicted point O B (ii) a Wherein the distance D is set such that all points: o is up 、O down 、O L 、O R 、O A 、O B Are all in the current indoor space;
respectively detecting O through the air quality detection module up 、O down 、O L 、O R 、O A 、O B The concentration of air pollutants at each point, denoted C in turn up 、C down 、C L 、C R 、C A 、C B ；
Detecting and recording all points through the positioning module: o is G 、O up 、O down 、O L 、O R 、O A 、O B The spatial position coordinates of (a);
each point is: o is G 、O up 、O down 、O L 、O R 、O A 、O B Spatial position coordinates of (a), air pollutant concentration at each point: c G 、C up 、C down 、C L 、C R 、C A 、C B And combining the distance D into a unit area data s;
1-1-3) collecting a plurality of unit area data s according to the steps 1-1-1) to 1-1-2);
1-1-4) detecting an environmental parameter H in the current indoor space through the environmental parameter detection module, where the environmental parameter H includes a temperature T, a humidity RH, an air pressure P, and an air flow velocity V, and is denoted as H = (T, RH, P, V);
1-1-5) combining the environmental parameters H and all the acquired unit area data S to form a data set, namely a training data set S, and storing the data set in the database;
2) Training a network model:
2-1) for each air contaminant Wi, at reference point O in each unit area data s G Spatial position coordinates of (1), reference point O G Concentration C of Wi GWi Distance D and environment parameter H as input, and each unit area data s is compared with reference point O G All corresponding predicted points: o is up 、O down 、O L 、O R 、O A 、O B Concentration C of air pollutants Wi upWi 、C downWi 、C LWi 、C RWi 、C AWi 、C BWi For output, the three machine learning models of LDA, kNN and SVMs are trained by adopting the training data set S, and each machine learning model obtains a prediction relational expression group F of the air pollutants Wi Wi ，F Wi Comprising f1 Wi 、f2 Wi 、f3 Wi 、f4 Wi 、f5 Wi 、f6 Wi Is marked as F Wi ＝(f1 Wi ,f2 Wi ,f3 Wi ,f4 Wi ,f5 Wi ,f6 Wi )；
Wherein, f1 Wi Represents: air contaminant Wi at predicted point O up Concentration of (C) upWi At a reference point O G Concentration of C GWi Difference value Δ 1 therebetween Wi Is identical to O up And O G The relationship between the distance D directly above and the environmental parameter H is denoted by Δ 1 Wi ＝f1 Wi (D Oup-OG ,H)；
F2 Wi Represents: c downWi And C GWi Difference value Δ 2 between Wi Is identical to O down And O G The relationship between the distance D directly below and the environmental parameter H is represented by Δ 2 Wi ＝f2 Wi (D Odown-OG ,H)；
F3 Wi Represents: c LWi And C GWi Difference value Δ 3 therebetween Wi Is identical to O L And O G The relationship between the distance D between the right and left and the environmental parameter H, denoted by Δ 3 Wi ＝f3 Wi (D OL-OG ,H)；
F4 Wi Represents: c RWi And C GWi Difference Δ 4 therebetween Wi Is identical to O R And O G The relationship between the distance D between the right and the left and the environmental parameter H is represented by Δ 4 Wi ＝f4 Wi (D OR-OG ,H)；
F5 Wi Represents: c AWi And C GWi Difference Δ 5 therebetween Wi Is identical to O A And O G The relationship between the distance D between the straight ahead and the environmental parameter H is denoted by Δ 5 Wi ＝f5 Wi (D OA-OG ,H)；
F6 Wi Represents: c BWi And C GWi Difference Δ 6 therebetween Wi Is identical to O B And O G The relationship between the distance D between the right and the rear and the environmental parameter H is denoted by Δ 6 Wi ＝f6 Wi (D OB-OG ,H)；
2-2) obtaining a prediction relational expression group F by three machine learning models of LDA, kNN and SVMs respectively Wi Reference point O in each piece of cell region data s G Spatial position coordinates and reference points ofO G Concentration C of Wi of GWi Distance D and environment parameter H as input, and each unit area data s is compared with reference point O G All corresponding predicted points: o is up 、O down 、O L 、O R 、O A 、O B Concentration C of air pollutant Wi of upWi 、C downWi 、C LWi 、C RWi 、C AWi 、C BWi Training the stacked network model for output;
2-3) finishing the training of the data of each air pollutant Wi according to the steps 2-1) to 2-2) to obtain a trained first prediction network model and a trained second prediction network model;
3) Detecting the concentration of air pollutants at a plurality of sampling points in the indoor space to be detected by the air quality detection device, and taking the sampling points as reference points O G Simultaneously detecting the environmental parameters H in the indoor space to be detected by the environmental parameter detection module, and then detecting a plurality of reference points O G Inputting the parameters into the prediction module together with the environmental parameters H, and outputting the prediction through the second prediction network model to obtain the parameters of each reference point O G The concentrations of various air pollutants at 6 corresponding prediction points respectively;
4) The model building and data calculating unit builds a concentration distribution model of various air pollutants in the indoor space to be measured according to the concentrations of various air pollutants at all the reference points and the prediction points; for each air pollutant Wi, the average value of the concentrations at all the reference points and the predicted points is taken as the average concentration of the air pollutant Wi, so as to obtain the average concentration of each air pollutant.
2. The air quality detection device according to claim 1, wherein the air quality detection module includes at least a PM2.5 detection sensor, a formaldehyde detection sensor, and a Volatile Organic Compound (VOC) detection sensor.
3. The air quality detection device of claim 2, further comprising a distance measurement module configured to detect a distance between the air quality detection device and an obstacle in real time, and a navigation module configured to provide assisted navigation to the movement module to enable the air quality detection module to move indoors according to a predetermined trajectory.
4. The air quality detection device according to claim 1, wherein the sampling points include at least 4 sampling points spaced apart from each other, and the 4 sampling points are not located in the same horizontal plane or the same vertical plane at the same time.
5. An air quality detecting method for detecting the concentration of air pollutants in an indoor space by using the air quality detecting apparatus according to any one of claims 1 to 4, the method comprising the steps of:
s1, controlling the moving module and the lifting module through the control module, moving the air quality detection device to an indoor space to be detected, and detecting the concentration of air pollutants at least 4 sampling points, wherein the at least 4 sampling points are not in the same horizontal plane or the same vertical plane at the same time; in the detection process, the moving module realizes the movement of the air quality detection device in the horizontal direction, and the lifting module realizes the movement of the air quality detection module in the vertical direction;
s2, the environmental parameter detection module simultaneously detects the environmental parameters in the indoor space to be detected;
s3, the prediction module receives detection results of the air quality detection module and the environmental parameter detection module, and predicts a concentration distribution model of various air pollutants in the indoor space to be detected and an average concentration of various air pollutants;
and S4, the display module displays the detection results of the air quality detection module and the environmental parameter detection module and the prediction result of the prediction module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210362248.7A CN114689478B (en) | 2022-04-08 | 2022-04-08 | Air quality detection device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210362248.7A CN114689478B (en) | 2022-04-08 | 2022-04-08 | Air quality detection device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114689478A CN114689478A (en) | 2022-07-01 |
| CN114689478B true CN114689478B (en) | 2022-11-15 |
Family
ID=82142276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210362248.7A Active CN114689478B (en) | 2022-04-08 | 2022-04-08 | Air quality detection device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114689478B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113188968A (en) * | 2021-05-06 | 2021-07-30 | 长沙理工大学 | Air pollutant concentration prediction method and system based on combined deep learning model |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7302313B2 (en) * | 2001-02-07 | 2007-11-27 | Aircuity, Inc. | Air quality monitoring systems and methods |
| CN108053071A (en) * | 2017-12-21 | 2018-05-18 | 宇星科技发展(深圳)有限公司 | Regional air pollutant concentration Forecasting Methodology, terminal and readable storage medium storing program for executing |
| US10684215B2 (en) * | 2018-01-25 | 2020-06-16 | Ludlum Measurements, Inc. | Method for measuring air pollutants using a folded tubular photometer |
| CN108984960B (en) * | 2018-08-14 | 2023-01-31 | 山东益华通润环保科技有限公司 | Rapid and accurate positioning and sampling point distribution method for volatile organic pollution |
| CN109696525A (en) * | 2019-02-12 | 2019-04-30 | 北京草木元人工环境技术有限公司 | A kind of air parameter solid auto-mapping system |
| CN211179747U (en) * | 2019-12-06 | 2020-08-04 | 甘肃易通环境监测有限公司 | Portable indoor air detection device |
| CN211178590U (en) * | 2019-12-30 | 2020-08-04 | 河南氧仕多生态物联科技有限公司 | Movable detection robot for air quality of indoor environment |
| CN111343279A (en) * | 2020-03-04 | 2020-06-26 | 兰州理工大学 | Air pollution detection and alarm system based on big data and cloud computing |
| CN112113603B (en) * | 2020-04-20 | 2021-07-23 | 中国矿业大学 | Indoor multi-source environment health index monitoring and evaluating method based on mobile robot |
| CN111563331B (en) * | 2020-05-08 | 2023-04-07 | 浙江工业大学 | Regional atmosphere pollution distribution prediction method based on mobile monitoring |
| CN113203831A (en) * | 2021-04-19 | 2021-08-03 | 南京市高淳区建程工程质量检测有限公司 | Indoor air harmful substance detection system |
| CN113837361A (en) * | 2021-09-01 | 2021-12-24 | 中咨公路养护检测技术有限公司 | Air pollutant concentration prediction method and system |
-
2022
- 2022-04-08 CN CN202210362248.7A patent/CN114689478B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113188968A (en) * | 2021-05-06 | 2021-07-30 | 长沙理工大学 | Air pollutant concentration prediction method and system based on combined deep learning model |
Non-Patent Citations (1)
| Title |
|---|
| 黑龙江省空气负离子浓度空间分布预测;王吉祥等;《湖北农业科学》;20180310(第05期);第24-29页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114689478A (en) | 2022-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105043396B (en) | The method and system of self-built map in a kind of mobile robot room | |
| Sprunk et al. | An experimental protocol for benchmarking robotic indoor navigation | |
| CN108120661B (en) | Method for measuring space-time distribution of particulate matter content in urban air | |
| Ramos et al. | Tools to improve built environment data collection for indoor microbial ecology investigations | |
| CN101140288A (en) | Central air-conditioning flue pipe air quality remote analysis system and method thereof | |
| CN114298557A (en) | Community environment quality analysis method and device | |
| CN114689478B (en) | Air quality detection device and method | |
| EP4279894A1 (en) | Method and system for locating and quantifying fugitive emission leaks | |
| US20230176024A1 (en) | System and method for characterizing, monitoring, & detecting bioaerosol presence & movement in an indoor environment | |
| US20210110607A1 (en) | System and Method for Mapping an Interior Space | |
| KR102333279B1 (en) | Indoor air quality evaluation service providing equipment, method and system | |
| US20220034540A1 (en) | Sensor network for validation of healthy buildings and transportation systems | |
| Wu et al. | An intelligent environmental monitoring system based on autonomous mobile robot | |
| Wada et al. | Collecting a database for studying gas distribution mapping and gas source localization with mobile robots | |
| CN209589073U (en) | A kind of high-throughput crop phenotype robot based on field | |
| Lilienthal et al. | Indicators of gas source proximity using metal oxide sensors in a turbulent environment | |
| CN111999756A (en) | Full-automatic tritium surface pollution patrol detection system and application method | |
| WO2023008322A1 (en) | Control method for sampling device, sampling device, and sampling system | |
| CN103292789A (en) | Positioning method and electronic equipment | |
| Khoshelham et al. | The ISPRS benchmark on indoor modelling: preliminary results | |
| JP2020139665A (en) | Dirt prediction system | |
| CN115717890A (en) | Clean room cleanliness detection method based on robot inspection | |
| Chen et al. | KeJia-LC: a low-cost mobile robot platform—champion of demo challenge on benchmarking service robots at RoboCup 2015 | |
| KR20200109646A (en) | Device of the efficient planning of air purifiers | |
| CN115738149B (en) | Fire monitor flame tracking method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |