CN108469273A - High in the clouds data joint debugging calibration method based on machine learning algorithm - Google Patents
High in the clouds data joint debugging calibration method based on machine learning algorithm Download PDFInfo
- Publication number
- CN108469273A CN108469273A CN201810162107.4A CN201810162107A CN108469273A CN 108469273 A CN108469273 A CN 108469273A CN 201810162107 A CN201810162107 A CN 201810162107A CN 108469273 A CN108469273 A CN 108469273A
- Authority
- CN
- China
- Prior art keywords
- data
- station
- monitoring
- micro
- calibration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D18/00—Testing or calibrating apparatus or arrangements provided for in groups G01D1/00 - G01D15/00
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The present invention discloses a kind of high in the clouds data joint debugging calibration method based on machine learning algorithm, belong to air monitering technical field, including gridding air monitering platform, cloud server and equipment management system, gridding air monitering platform provides air pollutants and the meteorological data of the micro- station of air quality monitoring in grid and the acquisition of national standard monitoring station, and by the Hbase databases in the data transmission to cloud server of acquisition；Cloud server reads the data at the micro- station and national standard monitoring station of the air quality monitoring in the Hbase databases in cloud server, it is compared by data consistency, judge whether the micro- station data of air quality monitoring deviate, if data deviate, data calibration is carried out using data calibration mould, exports calibration parameter；Calibration parameter is passed to equipment management system by cloud server by communication unit, can effectively solve the problem that the micro- station Data Data offset problem of air quality monitoring, high in the clouds is calibrated automatically, to ensure the availability of monitoring data quality.
Description
Technical field
The present invention relates to a kind of high in the clouds data joint debugging calibration method based on machine learning algorithm, belongs to air monitering technology
Field.
Background technology
In recent years, the PM2.5/PM10 in air pollution getting worse, especially air, the SO2/CO/NO2/ in air
The concentration of O3 increases, and seriously threatens people's health and daily life, solid in view of Environmental Protection Agency's air quality sensor monitoring technology
Some monitoring characteristics, such as with the growth of time, serious drift occurs for sensing characteristics, and the monitoring numerical value of previous calibration is caused to go out
Existing larger fluctuation, and artificial discovery, undoubtedly workload is huge for the work such as calibration again.
Invention content
The purpose of the present invention is to provide a kind of high in the clouds data joint debugging calibration method based on machine learning algorithm, Neng Gouyou
Effect solves the micro- station Data Data offset problem of air quality monitoring, and high in the clouds calibrates automatically, to ensure monitoring data quality can
The property used.
High in the clouds data joint debugging calibration method of the present invention based on machine learning algorithm, including gridding air monitering
Platform, cloud server and equipment management system, gridding air monitering platform respectively with cloud server and equipment management system
System connection realizes that data communication, method include the following steps：
S1：Gridding air monitering platform provides the micro- station of air quality monitoring in grid and the acquisition of national standard monitoring station
Air pollutants and meteorological data, and by the Hbase databases in the data transmission to cloud server of acquisition；
S2：Cloud server reads the micro- station of air quality monitoring and country in the Hbase databases in cloud server
The data at standard monitoring station, are compared by data consistency, judge whether the micro- station data of air quality monitoring deviate, if data are inclined
From, use data calibration model carry out data calibration, export calibration parameter；
S3：Calibration parameter is passed to equipment management system, equipment management system handle by cloud server by communication unit
Calibration command is distributed to each micro- station equipment of air quality monitoring in net region, and the micro- station of air quality monitoring is joined according to calibration
Number executes operation, and the data after calibration are uploaded to gridding air monitering platform.
Obtain air pollutants and the wind such as PM2.5, the SO2 at the micro- station of air quality monitoring in net region and national standard station
To meteorological elements such as/humitures, gas sensor and particulate matter sensors monitoring data and mark are extracted by establishing regression model
Regularity between quasi- examination station, cloud server end on-line training regression model, the changing rule for parsing sensing characteristics pass through number
Calibration parameter is calculated according to calibrating patterns, passes to equipment management system, equipment management system sends out instruction execution school to equipment
Quasi- operation.To ensure the availability of monitoring data quality, there is high in the clouds transfer matic calibration function, correct sensor drift automatically
And environmental disturbances, without live manual calibration.
Data consistency comparison is by calculating the micro- station of air quality monitoring and national standard monitoring in the step S2
The related coefficient and irrelevance of data judge whether data deviate in certain period of time of standing, and decision condition includes that related coefficient is sentenced
Fixed condition and irrelevance decision condition, wherein related coefficient decision condition are as follows：
Wherein, in decision condition (1)：S1=(x1, x2 ..., xn) indicates the micro- station certain period of time of air quality monitoring
Interior monitoring data set；S2=(y1, y2 ..., yn) indicates the monitoring data in the certain period of time of national standard monitoring station
Set；Corr indicates the calculating of the simple correlation coefficient between multiple variables；M is related coefficient, value 0.8.
The irrelevance decision condition is as follows：
Wherein, in decision condition (2)：AvgIx=(x1+x2+...+xn)/n indicates the micro- station of air quality monitoring and country
The average value of monitoring data in the certain period of time of standard monitoring station；
AvgIY=(y1+y2+...+yn)/n indicates being averaged for monitoring data in the certain period of time of national standard monitoring station
Value；
N is constant, value 20；
When decision condition (1) and decision condition (2) while when meeting, then judge data without departing from；When decision condition (1) and
It is any when being unsatisfactory in decision condition (2), then judge that data deviate.
Cloud server uses data calibration model in the step S3, reads air quality in Hbase databases and supervises
The data at micrometer station and national standard monitoring station, cloud server end on-line training regression model, the variation rule for parsing sensing characteristics
Rule captures data rule, by Linear Regression linear regressions, exports calibration parameter, sends equipment management system to
System.
The Linear Regression linear regressions specifically include following steps：
S11：Acquire S1=(x1, x2 ..., xn), S2=(y1, y2 ..., yn) two datasets；
S12：Simulation S1=k*S2+b data sets train relevant coefficient k=0.3682, b=by linear regression
19.5；
S13：Calibration parameter k=0.3682, b=19.5 are exported, sends equipment management system to, equipment management system is school
Quasi instruction is distributed to each micro- station equipment of air quality monitoring in net region, and the micro- station equipment of air quality monitoring is according to calibration
Parameter executes operation, and the data of the S1 after calibration are uploaded to gridding air monitering platform.
The micro- station of the air quality monitoring includes gas sensor and particulate matter sensors, and particulate matter sensors are by swashing
Light scattering method monitors the PM2.5/PM10 concentration of air, and gas sensor monitors the SO2/CO/ in air by electrochemical process
NO2/O3 concentration.
Compared with prior art, the present invention having the advantages that：
High in the clouds data joint debugging calibration method of the present invention based on machine learning algorithm, can effectively solve the problem that air matter
Amount monitors micro- station Data Data offset problem, and high in the clouds is calibrated automatically, to ensure the availability of monitoring data quality, obtains grid
The air pollutants and wind direction/humiture etc. such as PM2.5, the SO2 at the micro- station of air quality monitoring and national standard monitoring station in region
Meteorological element is extracted by establishing regression model between gas sensor and particulate matter sensors monitoring data and standard check station
Regularity, cloud server end on-line training regression model, parse sensing characteristics changing rule, pass through data calibration model meter
Calibration parameter is calculated, passes to equipment management system, equipment management system sends out instruction execution calibration operation to equipment, to protect
The availability of monitoring data quality is demonstrate,proved, scheme provided by the invention has high in the clouds transfer matic calibration function, corrects sensor automatically
Drift and environmental disturbances, without live manual calibration.
Description of the drawings
Fig. 1 is that the present invention is based on the flow diagrams of the high in the clouds data joint debugging calibration method of machine learning algorithm；
Fig. 2 is the data and curves before the micro- station alignment of air quality monitoring in the embodiment of the present invention；
Fig. 3 is the data and curves after the micro- station alignment of air quality monitoring in the embodiment of the present invention.
Specific implementation mode
The present invention is further illustrated with reference to the accompanying drawings and examples：
Embodiment：
As shown in Figs. 1-3, the high in the clouds data joint debugging calibration method of the present invention based on machine learning algorithm, including net
Format air monitering platform, cloud server and equipment management system, gridding air monitering platform respectively with cloud server
It is connected with equipment management system and realizes that data communication, method include the following steps：
S1：Gridding air monitering platform provides the micro- station of air quality monitoring in grid and the acquisition of national standard monitoring station
Air pollutants and meteorological data, and by the Hbase databases in the data transmission to cloud server of acquisition；
S2：Cloud server reads the micro- station of air quality monitoring and country in the Hbase databases in cloud server
The data at standard monitoring station, are compared by data consistency, judge whether the micro- station data of air quality monitoring deviate, if data are inclined
From, use data calibration model carry out data calibration, export calibration parameter；
S3：Calibration parameter is passed to equipment management system, equipment management system handle by cloud server by communication unit
Calibration command is distributed to each micro- station equipment of air quality monitoring in net region, and the micro- station of air quality monitoring is joined according to calibration
Number executes operation, and the data after calibration are uploaded to gridding air monitering platform.
Data consistency comparison is by calculating the micro- station of air quality monitoring and national standard monitoring in the step S2
The related coefficient and irrelevance of data judge whether data deviate in certain period of time of standing, and decision condition includes that related coefficient is sentenced
Fixed condition and irrelevance decision condition, decision condition are as follows：
Wherein, in decision condition (1)：S1=(x1, x2 ..., xn) indicates the micro- station certain period of time of air quality monitoring
Interior monitoring data set；S2=(y1, y2 ..., yn) indicates the monitoring data in the certain period of time of national standard monitoring station
Set；Corr indicates the calculating of the simple correlation coefficient between multiple variables；M is related coefficient, value 0.8；
Wherein, in decision condition (2)：AvgIx=(x1+x2+...+xn)/n indicates the micro- station of air quality monitoring and country
The average value of monitoring data in the certain period of time of standard monitoring station；
AvgIY=(y1+y2+...+yn)/n indicates being averaged for monitoring data in the certain period of time of national standard monitoring station
Value；
N is constant, value 20；
When decision condition (1) and decision condition (2) while when meeting, then judge data without departing from；When decision condition (1) and
It is any when being unsatisfactory in decision condition (2), then judge that data deviate.
Cloud server uses data calibration model in the step S3, reads air quality in Hbase databases and supervises
The data at micrometer station and national standard monitoring station, cloud server end on-line training regression model, the variation rule for parsing sensing characteristics
Rule captures data rule, by Linear Regression linear regressions, exports calibration parameter, sends equipment management system to
System.
As Figure 2-3, before calibration crawl air quality monitoring micro- station and national standard monitoring station two groups of data, in figure
1- indicates that national standard station monitoring data curve, 2- indicate the micro- station data and curves of air quality monitoring, the data acquisition system before calibration
S1=[371 221 180 188 200 153 134 126 118 105 72 61 72 97 73 75 77 95 114 132
125 131 141 132 159 163 168 164 170 186 162 148 158 201 235 200 170 105 88 87
99 126 215 260 230 231 257 284 340 368 369 383 396 396 409 488 539 515 436
390 320 326 342 354 361 417 492 557 560 683 695 671 681 716 688 589 570 537
532 527 554 393 435 326 143 58 56 37 41 43 40 46 49 38 38 38 38 60 68 88 133
158 151 95 66 46 38 44 49 56 66 93 115 118 122 170 181 156 151 162 141 133
143 166 161 166 163 149 120 112 96 86 88 92 109 125 156 149 144 150 178 175
167 168 164 178 215 214 212 205 201 168 121 67 44 40 41 54 70 82 129 122 102
112], [187 158 109 69 52 56 54 48 44 43 41 31 25 27 38 46 49 44 38 40 48 S2=
55 53 52 53 59 60 60 57 55 58 58 59 56 60 62 64 63 60 51 45 39 46 58 78 84 89
84 92 98 110 116 116 117 118 126 134 151 164 169 157 138 125 131 139 148 155
170 183 188 204 214 228 220 218 223 212 202 191 187 184 187 184 142 129 115
88 61 44 41 33 31 32 32 37 34 36 31 35 42 53 63 72 75 66 54 42 36 34 36 39 44
55 65 78 78 88 95 99 93 86 83 81 80 84 90 93 90 84 76 68 65 62 62 58 63 68 81
87 95 93 99 102 104 104 104 108 117 124 133 130 128 114 95 70 51 36 32 32 38
50 65 74 76], avgIx=206, avgIY=88, n value be 20, avgIx-avgIY=118, hence it is evident that be more than 20. so,
This time data deviate.
Homologous thread data correspond to table before table 1- calibrations
| On call time | National standard monitoring station | The micro- station of air quality monitoring |
| 2017-12-0401:00 | 187 | 371.056491 |
| 2017-12-0407:00 | 54 | 133.9570885 |
| 2017-12-0413:00 | 25 | 71.89570885 |
| 2017-12-0419:00 | 38 | 114.0874525 |
| 2017-12-0501:00 | 53 | 158.7941336 |
| 2017-12-0507:00 | 58 | 161.8332428 |
| 2017-12-0513:00 | 64 | 169.5274307 |
| 2017-12-0519:00 | 46 | 214.8940793 |
| 2017-12-0601:00 | 92 | 340.2118414 |
| 2017-12-0607:00 | 118 | 409.0086909 |
| 2017-12-0613:00 | 157 | 320.3720804 |
| 2017-12-0619:00 | 155 | 491.9989136 |
| 2017-12-0701:00 | 228 | 681.0727865 |
| 2017-12-0707:00 | 191 | 531.6892993 |
| 2017-12-0716:00 | 129 | 143.1015752 |
| 2017-12-0722:00 | 33 | 39.95654536 |
| 2017-12-0804:00 | 36 | 38.21564367 |
| 2017-12-0810:00 | 72 | 151.3688213 |
| 2017-12-0816:00 | 34 | 48.56871266 |
| 2017-12-0822:00 | 78 | 122.2732211 |
| 2017-12-0904:00 | 86 | 140.8527974 |
| 2017-12-0910:00 | 93 | 162.9060293 |
| 2017-12-0916:00 | 62 | 88.22922325 |
| 2017-12-0922:00 | 87 | 143.9054861 |
| 2017-12-1004:00 | 104 | 164.4513851 |
| 2017-12-1010:00 | 130 | 200.8392178 |
| 2017-12-1016:00 | 36 | 40.98044541 |
| 2017-12-1022:00 | 74 | 101.6811515 |
As shown in Figure 2 and Table 1, in Fig. 2 abscissa indicate on call time, ordinate indicate monitoring data, before calibration on
It calls time corresponding with the data of national standard monitoring station and the micro- station of air quality monitoring as shown in table 1.
The Linear Regression linear regressions specifically include following steps：
S11：Acquire S1=(x1, x2 ..., xn), S2=(y1, y2 ..., yn) two datasets；
S12：Simulation S1=k*S2+b data sets train relevant coefficient k=0.3682, b=by linear regression
19.5；
S13：Calibration parameter k=0.3682, b=19.5 are exported, sends equipment management system to, equipment management system is school
Quasi instruction is distributed to each micro- station equipment of air quality monitoring in net region, and the micro- station equipment of air quality monitoring is according to calibration
Parameter executes operation, and the data of the S1 after calibration are uploaded to gridding air monitering platform.
Specific implementation is S1=(x1, x2 ..., xn), S2=(y1, y2 ..., yn) two datasets, simulates S1
=k*S2+b data sets train relevant coefficient k=0.3682, b=19.5 by linear regression, export calibration parameter, pass
To equipment management system, after calibration, avgIx=95, avgIY=88, avgIx-avgIY=7, less than 20, and correlation coefficient r=
0.8925. it is more than 0.80, meets condition, data are without departing from the data acquisition system S1=[156 101 86 89 93 76 after calibration
69 66 63 58 46 42 46 55 46 47 48 54 62 68 65 68 71 68 78 79 81 80 82 88 79 74
78 94 10693 82 58 52 52 56 66 99 115 104 104 114 124 145 155 155 161 165 165
170 199 218 209 180 163 137 139 145 150 152 173 201 225 226 271 275 267 270
283 273 236 229 217 215 214 224 164 180 139 72 41 40 33 34 35 34 36 37 34 34
34 34 41 45 52 69 78 75 54 44 36 33 36 37 40 44 54 62 63 65 82 86 77 75 79 71
69 72 81 79 81 79 74 64 61 55 51 52 54 60 66 77 74 72 75 85 84 81 81 80 85 99
98 98 95 93 81 64 44 36 34 35 39 45 50 67 64 57 61]；
Homologous thread data correspond to table after table 2- calibrations
| On call time | National standard station | The micro- station of air monitering |
| 2017-12-0401:00 | 187 | 156.123 |
| 2017-12-0407:00 | 54 | 68.823 |
| 2017-12-0413:00 | 25 | 45.972 |
| 2017-12-0419:00 | 38 | 61.507 |
| 2017-12-0501:00 | 53 | 77.968 |
| 2017-12-0507:00 | 58 | 79.087 |
| 2017-12-0513:00 | 64 | 81.92 |
| 2017-12-0519:00 | 46 | 98.624 |
| 2017-12-0601:00 | 92 | 144.766 |
| 2017-12-0607:00 | 118 | 170.097 |
| 2017-12-0613:00 | 157 | 137.461 |
| 2017-12-0619:00 | 155 | 200.654 |
| 2017-12-0701:00 | 228 | 270.271 |
| 2017-12-0707:00 | 191 | 215.268 |
| 2017-12-0716:00 | 129 | 72.19 |
| 2017-12-0722:00 | 33 | 34.212 |
| 2017-12-0804:00 | 36 | 33.571 |
| 2017-12-0810:00 | 72 | 75.234 |
| 2017-12-0816:00 | 34 | 37.383 |
| 2017-12-0822:00 | 78 | 64.521 |
| 2017-12-0904:00 | 86 | 71.362 |
| 2017-12-0910:00 | 93 | 79.482 |
| 2017-12-0916:00 | 62 | 51.986 |
| 2017-12-0922:00 | 87 | 72.486 |
| 2017-12-1004:00 | 104 | 80.051 |
| 2017-12-1010:00 | 130 | 93.449 |
| 2017-12-1016:00 | 36 | 34.589 |
| 2017-12-1022:00 | 74 | 56.939 |
As shown in Fig. 3 and table 2, abscissa indicates to call time in Fig. 3, and ordinate indicates the data of monitoring, after calibration
On call time it is corresponding with the data of national standard monitoring station and the micro- station of air quality monitoring as shown in table 2, the data after calibration
Curve S1 and national standard monitoring station data and curves S2 are almost the same.
The micro- station of the air quality monitoring includes gas sensor and particulate matter sensors, and particulate matter sensors are by swashing
Light scattering method monitors the PM2.5/PM10 concentration of air, and gas sensor monitors the SO2/CO/ in air by electrochemical process
NO2/O3 concentration.Using the high in the clouds data connection based on machine learning algorithm of the embodiment of the present invention described above in association with attached drawing
Calibration method is adjusted, can effectively solve the problem that the micro- station Data Data offset problem of air quality monitoring, high in the clouds is calibrated automatically, to ensure
The availability of monitoring data quality.But the present invention is not limited to described embodiment, do not depart from the principle of the present invention and
These variation, modification, replacement and deformations for being carried out to embodiment are still fallen in protection scope of the present invention in the case of spirit.
Claims (6)
1. a kind of high in the clouds data joint debugging calibration method based on machine learning algorithm, including gridding air monitering platform, high in the clouds
Server and equipment management system, gridding air monitering platform connect realization with cloud server and equipment management system respectively
Data communication, it is characterised in that：The method includes the following steps：
S1：Gridding air monitering platform provides the air at the micro- station and the acquisition of national standard monitoring station of air quality monitoring in grid
Pollutant and meteorological data, and by the Hbase databases in the data transmission to cloud server of acquisition；
S2：Cloud server reads the micro- station of air quality monitoring and national standard in the Hbase databases in cloud server
The data of monitoring station, are compared by data consistency, judge whether the micro- station data of air quality monitoring deviate, if data deviate,
Data calibration is carried out using data calibration model, exports calibration parameter；
S3：Calibration parameter is passed to equipment management system by cloud server by communication unit, and equipment management system is calibration
Instruction is distributed to each micro- station equipment of air quality monitoring in net region, and the micro- station of air quality monitoring is held according to calibration parameter
Row operation, and the data after calibration are uploaded to gridding air monitering platform.
2. the high in the clouds data joint debugging calibration method according to claim 1 based on machine learning algorithm, it is characterised in that：Institute
Data consistency comparison is by calculating the micro- station of air quality monitoring and national standard monitoring station certain time in the step S2 stated
The related coefficient and irrelevance of data judge whether data deviate in section, and decision condition includes related coefficient decision condition and partially
From degree decision condition, wherein related coefficient decision condition is as follows：
Wherein, in decision condition (1)：S1=(x1, x2 ..., xn) is indicated in the micro- station certain period of time of air quality monitoring
Monitoring data set；S2=(y1, y2 ..., yn) indicates the monitoring data set in the certain period of time of national standard monitoring station；
Corr indicates the calculating of the simple correlation coefficient between multiple variables；
M is related coefficient, value 0.8.
3. the high in the clouds data joint debugging calibration method according to claim 2 based on machine learning algorithm, it is characterised in that：Institute
The irrelevance decision condition stated is as follows：
Wherein, in decision condition (2)：AvgIx=(x1+x2+...+xn)/n indicates the micro- station of air quality monitoring and national standard
The average value of monitoring data in the certain period of time of monitoring station；
AvgIY=(y1+y2+...+yn)/n indicates the average value of monitoring data in the certain period of time of national standard monitoring station；
N is constant, value 20；
When decision condition (1) and decision condition (2) while when meeting, then judge data without departing from；
When in decision condition (1) and decision condition (2) it is any be unsatisfactory for when, then judge data deviate.
4. the high in the clouds data joint debugging calibration method according to claim 1 based on machine learning algorithm, it is characterised in that：Institute
Cloud server uses data calibration model in the step S3 stated, reads the micro- station of air quality monitoring and state in Hbase databases
The data at family's standard monitoring station, cloud server end on-line training regression model, the changing rule for parsing sensing characteristics capture data
Rule exports calibration parameter, sends equipment management system to by Linear Regression linear regressions.
5. the high in the clouds data joint debugging calibration method according to claim 4 based on machine learning algorithm, it is characterised in that：Institute
The Linear Regression linear regressions stated specifically include following steps：
S11：Acquire S1=(x1, x2 ..., xn), S2=(y1, y2 ..., yn) two datasets；
S12：Simulation S1=k*S2+b data sets train relevant coefficient k=0.3682, b=19.5 by linear regression；
S13：Calibration parameter k=0.3682, b=19.5 are exported, sends equipment management system to, equipment management system refers to calibration
Order is distributed to each micro- station equipment of air quality monitoring in net region, and the micro- station equipment of air quality monitoring is according to calibration parameter
Operation is executed, and the data of the S1 after calibration are uploaded to gridding air monitering platform.
6. the high in the clouds data joint debugging calibration method according to claim 1 based on machine learning algorithm, it is characterised in that：Institute
The micro- station of air quality monitoring stated includes gas sensor and particulate matter sensors, and particulate matter sensors are supervised by laser scattering method
The PM2.5/PM10 concentration of air is surveyed, gas sensor monitors the SO2/CO/NO2/O3 concentration in air by electrochemical process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810162107.4A CN108469273A (en) | 2018-02-27 | 2018-02-27 | High in the clouds data joint debugging calibration method based on machine learning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810162107.4A CN108469273A (en) | 2018-02-27 | 2018-02-27 | High in the clouds data joint debugging calibration method based on machine learning algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108469273A true CN108469273A (en) | 2018-08-31 |
Family
ID=63264948
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810162107.4A Pending CN108469273A (en) | 2018-02-27 | 2018-02-27 | High in the clouds data joint debugging calibration method based on machine learning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108469273A (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109613183A (en) * | 2019-01-03 | 2019-04-12 | 北京英视睿达科技有限公司 | Low accuracy monitoring device data revises method and system |
| CN109631973A (en) * | 2018-11-30 | 2019-04-16 | 苏州数言信息技术有限公司 | A kind of automatic calibrating method and system of sensor |
| CN110084379A (en) * | 2019-05-08 | 2019-08-02 | 东莞德福得精密五金制品有限公司 | The method that calibration instrument is calibrated is treated using artificial intelligence cloud computing |
| CN110333555A (en) * | 2019-07-19 | 2019-10-15 | 南京信息工程大学 | Mobile weather environment observation device and its calibration method |
| CN110426493A (en) * | 2019-08-01 | 2019-11-08 | 北京软通智慧城市科技有限公司 | Air quality monitoring data calibration method, device, equipment and storage medium |
| CN110672143A (en) * | 2019-11-07 | 2020-01-10 | 徐州陀微传感科技有限公司 | Sensor calibration method |
| CN111122668A (en) * | 2019-12-30 | 2020-05-08 | 江西飞尚科技有限公司 | Automatic-calibration air quality monitoring device and monitoring method thereof |
| CN111157413A (en) * | 2020-01-15 | 2020-05-15 | 北京师范大学 | PM2.5 gridding monitoring network system and consistency calibration method thereof |
| WO2020107445A1 (en) * | 2018-11-30 | 2020-06-04 | 苏州数言信息技术有限公司 | Automatic calibration method and system for sensor |
| CN111323544A (en) * | 2020-03-27 | 2020-06-23 | 沈阳沃尔鑫环保科技有限公司 | Calibration method and system based on miniature air quality monitoring instrument |
| CN111830210A (en) * | 2020-07-30 | 2020-10-27 | 广州交信投科技股份有限公司 | Air quality monitoring method, device and system and computer equipment |
| CN112394137A (en) * | 2019-08-14 | 2021-02-23 | 中国科学院沈阳计算技术研究所有限公司 | Intelligent calibration method for monitoring environmental air quality |
| CN112528566A (en) * | 2020-12-18 | 2021-03-19 | 江西理工大学南昌校区 | Real-time air quality data calibration method and system based on AdaBoost training model |
| CN112611688A (en) * | 2020-12-30 | 2021-04-06 | 罗克佳华科技集团股份有限公司 | Automatic calibration device and method for atmosphere monitoring equipment |
| CN113092681A (en) * | 2021-04-02 | 2021-07-09 | 河北先河环保科技股份有限公司 | Sensor pairing method and system for gridding monitoring network |
| CN113297528A (en) * | 2021-06-10 | 2021-08-24 | 四川大学 | NO based on multi-source big data2High-resolution space-time distribution calculation method |
| CN113358732A (en) * | 2020-07-21 | 2021-09-07 | 艾感科技(广东)有限公司 | Remote calibration method and system for gas sensor |
| CN113391040A (en) * | 2021-07-12 | 2021-09-14 | 北京清环宜境技术有限公司 | Data artificial intelligence automatic calibration method for atmospheric micro-station |
| CN114200077A (en) * | 2021-11-13 | 2022-03-18 | 安徽熵沃智能科技有限公司 | Cloud platform intelligent auxiliary calibration algorithm applied to gridding air quality monitoring system |
| CN115508511A (en) * | 2022-09-19 | 2022-12-23 | 中节能天融科技有限公司 | Sensor self-adaptive calibration method based on gridding equipment full-parameter feature analysis |
| CN116577469B (en) * | 2023-05-17 | 2024-01-23 | 广州德亨信息技术有限公司 | Atmospheric environment monitoring system and data prediction method based on data precision calibration |
| CN117591907A (en) * | 2024-01-18 | 2024-02-23 | 四川国蓝中天环境科技集团有限公司 | Pollution occurrence and propagation sensing method based on intensive air quality micro-station monitoring |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160142160A1 (en) * | 2014-11-03 | 2016-05-19 | Fujitsu Limited | Method of managing sensor network |
| CN105823812A (en) * | 2016-05-10 | 2016-08-03 | 泛测（北京）环境科技有限公司 | Air detector and working method thereof |
| CN106644862A (en) * | 2016-09-12 | 2017-05-10 | 济南诺方电子技术有限公司 | Sensor, monitoring station based on sensor and monitoring method of monitoring station |
| CN206594021U (en) * | 2014-12-02 | 2017-10-27 | 提赛环科仪器贸易（北京）有限公司 | Particle sensor component calibration system |
| CN107505005A (en) * | 2017-09-20 | 2017-12-22 | 广东先河科迪隆科技有限公司 | Industrial park ambient air quality supervisory systems |
-
2018
- 2018-02-27 CN CN201810162107.4A patent/CN108469273A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160142160A1 (en) * | 2014-11-03 | 2016-05-19 | Fujitsu Limited | Method of managing sensor network |
| CN206594021U (en) * | 2014-12-02 | 2017-10-27 | 提赛环科仪器贸易（北京）有限公司 | Particle sensor component calibration system |
| CN105823812A (en) * | 2016-05-10 | 2016-08-03 | 泛测（北京）环境科技有限公司 | Air detector and working method thereof |
| CN106644862A (en) * | 2016-09-12 | 2017-05-10 | 济南诺方电子技术有限公司 | Sensor, monitoring station based on sensor and monitoring method of monitoring station |
| CN107505005A (en) * | 2017-09-20 | 2017-12-22 | 广东先河科迪隆科技有限公司 | Industrial park ambient air quality supervisory systems |
Non-Patent Citations (1)
| Title |
|---|
| 河北省环境监测站: "《河北省环境空气自动站管理实用工作手册》", 30 September 2016, 河北科学技术出版社 * |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109631973A (en) * | 2018-11-30 | 2019-04-16 | 苏州数言信息技术有限公司 | A kind of automatic calibrating method and system of sensor |
| WO2020107445A1 (en) * | 2018-11-30 | 2020-06-04 | 苏州数言信息技术有限公司 | Automatic calibration method and system for sensor |
| CN109631973B (en) * | 2018-11-30 | 2021-04-16 | 苏州数言信息技术有限公司 | Automatic calibration method and system for sensor |
| CN109613183A (en) * | 2019-01-03 | 2019-04-12 | 北京英视睿达科技有限公司 | Low accuracy monitoring device data revises method and system |
| CN110084379A (en) * | 2019-05-08 | 2019-08-02 | 东莞德福得精密五金制品有限公司 | The method that calibration instrument is calibrated is treated using artificial intelligence cloud computing |
| CN110333555A (en) * | 2019-07-19 | 2019-10-15 | 南京信息工程大学 | Mobile weather environment observation device and its calibration method |
| CN110426493A (en) * | 2019-08-01 | 2019-11-08 | 北京软通智慧城市科技有限公司 | Air quality monitoring data calibration method, device, equipment and storage medium |
| CN110426493B (en) * | 2019-08-01 | 2021-10-29 | 北京软通智慧科技有限公司 | Air quality monitoring data calibration method, device, equipment and storage medium |
| CN112394137A (en) * | 2019-08-14 | 2021-02-23 | 中国科学院沈阳计算技术研究所有限公司 | Intelligent calibration method for monitoring environmental air quality |
| CN110672143A (en) * | 2019-11-07 | 2020-01-10 | 徐州陀微传感科技有限公司 | Sensor calibration method |
| CN111122668A (en) * | 2019-12-30 | 2020-05-08 | 江西飞尚科技有限公司 | Automatic-calibration air quality monitoring device and monitoring method thereof |
| CN111157413A (en) * | 2020-01-15 | 2020-05-15 | 北京师范大学 | PM2.5 gridding monitoring network system and consistency calibration method thereof |
| CN111157413B (en) * | 2020-01-15 | 2021-09-17 | 北京师范大学 | PM2.5 gridding monitoring network system and consistency calibration method thereof |
| CN111323544A (en) * | 2020-03-27 | 2020-06-23 | 沈阳沃尔鑫环保科技有限公司 | Calibration method and system based on miniature air quality monitoring instrument |
| CN113358732B (en) * | 2020-07-21 | 2023-10-24 | 艾感科技(广东)有限公司 | Remote calibration method and system for gas sensor |
| CN113358732A (en) * | 2020-07-21 | 2021-09-07 | 艾感科技(广东)有限公司 | Remote calibration method and system for gas sensor |
| CN111830210A (en) * | 2020-07-30 | 2020-10-27 | 广州交信投科技股份有限公司 | Air quality monitoring method, device and system and computer equipment |
| CN112528566A (en) * | 2020-12-18 | 2021-03-19 | 江西理工大学南昌校区 | Real-time air quality data calibration method and system based on AdaBoost training model |
| CN112611688A (en) * | 2020-12-30 | 2021-04-06 | 罗克佳华科技集团股份有限公司 | Automatic calibration device and method for atmosphere monitoring equipment |
| CN113092681B (en) * | 2021-04-02 | 2023-01-17 | 河北先河环保科技股份有限公司 | Sensor pairing method and system for gridding monitoring network |
| CN113092681A (en) * | 2021-04-02 | 2021-07-09 | 河北先河环保科技股份有限公司 | Sensor pairing method and system for gridding monitoring network |
| CN113297528B (en) * | 2021-06-10 | 2022-07-01 | 四川大学 | NO based on multi-source big data2High-resolution space-time distribution calculation method |
| CN113297528A (en) * | 2021-06-10 | 2021-08-24 | 四川大学 | NO based on multi-source big data2High-resolution space-time distribution calculation method |
| CN113391040A (en) * | 2021-07-12 | 2021-09-14 | 北京清环宜境技术有限公司 | Data artificial intelligence automatic calibration method for atmospheric micro-station |
| CN113391040B (en) * | 2021-07-12 | 2023-09-15 | 北京清环宜境技术有限公司 | Automatic calibration method for data artificial intelligence of atmospheric micro station |
| CN114200077A (en) * | 2021-11-13 | 2022-03-18 | 安徽熵沃智能科技有限公司 | Cloud platform intelligent auxiliary calibration algorithm applied to gridding air quality monitoring system |
| CN115508511A (en) * | 2022-09-19 | 2022-12-23 | 中节能天融科技有限公司 | Sensor self-adaptive calibration method based on gridding equipment full-parameter feature analysis |
| CN116577469B (en) * | 2023-05-17 | 2024-01-23 | 广州德亨信息技术有限公司 | Atmospheric environment monitoring system and data prediction method based on data precision calibration |
| CN117591907A (en) * | 2024-01-18 | 2024-02-23 | 四川国蓝中天环境科技集团有限公司 | Pollution occurrence and propagation sensing method based on intensive air quality micro-station monitoring |
| CN117591907B (en) * | 2024-01-18 | 2024-03-26 | 四川国蓝中天环境科技集团有限公司 | Pollution occurrence and propagation sensing method based on intensive air quality micro-station monitoring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108469273A (en) | High in the clouds data joint debugging calibration method based on machine learning algorithm | |
| CN104360667B (en) | A kind of polluter on-line monitoring platform and the anti-counterfeiting method of pollution source monitoring data | |
| CN106932543A (en) | Thermal power plant's environment flue gas monitoring early warning system | |
| CN114199962B (en) | Harmful gas analysis and monitoring system for livestock and poultry houses | |
| CN108333314A (en) | A kind of air pollution intelligent monitor system | |
| CN106198866B (en) | Farm air-quality monitoring system based on wireless sensor network | |
| CN104537568A (en) | Real-time on-line comprehensive assessment system of energy conservation and emission reduction performance of coal-fired power plant unit | |
| CN207456503U (en) | Livestock and poultry cultivation environmental monitoring system | |
| CN108802856B (en) | AI-based source data dynamic correction and forecast system and working method thereof | |
| CN109992740A (en) | A method of it is horizontal that pollution sources actual discharge being calculated based on database | |
| CN208076482U (en) | A kind of multicomponent VOCs gas monitoring systems | |
| CN116257540B (en) | Management method and management system for geographic environment data | |
| CN116028887B (en) | Analysis method of continuous industrial production data | |
| CN115979339B (en) | Intelligent monitoring system for laying hen breeding environment based on big data analysis | |
| CN114354783A (en) | Health degree evaluation method of extra-high voltage oil chromatography monitoring device based on-operation data | |
| CN114152896A (en) | Misalignment replacing system based on acquisition platform | |
| Liu et al. | Research on data correction method of micro air quality detector based on combination of partial least squares and random forest regression | |
| CN108387692A (en) | A kind of atmosphere pollution intelligent monitor system | |
| CN110400001B (en) | High-voltage cable inspection cycle optimization method based on risk assessment | |
| CN116467366A (en) | Block chain-based carbon footprint monitoring analysis and evaluation system | |
| CN108335233A (en) | A kind of intelligent grid metric data processing system based on big data technology | |
| CN102750815B (en) | Concentrator with environmental monitoring function and control method thereof | |
| CN112486230B (en) | Intelligent poultry breeding management system | |
| CN115423383B (en) | Distributed village and town drinking water monitoring and regulation system and method based on artificial intelligence | |
| CN107563608A (en) | A kind of power distribution communication net safety evaluation method |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201201 Address after: 272000 Shandong province Jining city science and Technology Exhibition Center Applicant after: INSTITUTE OF COMPUTING TECHNOLOGY, CHINESE ACADEMY OF SCIENCES Applicant after: JINING ZHONGKE YUNTIAN ENVIRONMENTAL PROTECTION TECHNOLOGY Co.,Ltd. Address before: 272000 Shandong city of Jining province city technology center four Applicant before: JINING ZHONGKE YUNTIAN ENVIRONMENTAL PROTECTION TECHNOLOGY Co.,Ltd. |
|
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Chen Yuanfei Inventor after: Zhou Dandan Inventor after: Ge Qingkun Inventor after: Lin Peng Inventor after: Tian Zhen Inventor before: Chen Yuanfei Inventor before: Zhou Dandan Inventor before: Meng Junwang Inventor before: Sun Yazhou Inventor before: Yang Peishuai |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180831 |