CN117330710A - Atmospheric pollution detection device and atmospheric pollution trend prediction method - Google Patents
Atmospheric pollution detection device and atmospheric pollution trend prediction method Download PDFInfo
- Publication number
- CN117330710A CN117330710A CN202311256930.9A CN202311256930A CN117330710A CN 117330710 A CN117330710 A CN 117330710A CN 202311256930 A CN202311256930 A CN 202311256930A CN 117330710 A CN117330710 A CN 117330710A
- Authority
- CN
- China
- Prior art keywords
- monitoring part
- mounting seat
- data
- atmospheric pollution
- detector
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 title claims abstract description 23
- 238000012544 monitoring process Methods 0.000 claims abstract description 107
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000003915 air pollution Methods 0.000 claims description 29
- 238000003860 storage Methods 0.000 claims description 15
- 239000003344 environmental pollutant Substances 0.000 claims description 14
- 231100000719 pollutant Toxicity 0.000 claims description 14
- 238000010586 diagram Methods 0.000 claims description 13
- 230000007246 mechanism Effects 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 6
- 230000036961 partial effect Effects 0.000 claims description 3
- 238000002759 z-score normalization Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 2
- 125000003003 spiro group Chemical group 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 5
- 230000008859 change Effects 0.000 description 15
- 230000012447 hatching Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 239000000356 contaminant Substances 0.000 description 6
- 230000002441 reversible effect Effects 0.000 description 5
- 239000013598 vector Substances 0.000 description 5
- 238000009792 diffusion process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000009434 installation Methods 0.000 description 4
- 101100206190 Arabidopsis thaliana TCP20 gene Proteins 0.000 description 3
- 101100082494 Oryza sativa subsp. japonica PCF1 gene Proteins 0.000 description 3
- 101100045761 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) TFC4 gene Proteins 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 3
- 230000000670 limiting effect Effects 0.000 description 3
- 238000007477 logistic regression Methods 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 244000037364 Cinnamomum aromaticum Species 0.000 description 1
- 235000014489 Cinnamomum aromaticum Nutrition 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 210000001061 forehead Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16M—FRAMES, CASINGS OR BEDS OF ENGINES, MACHINES OR APPARATUS, NOT SPECIFIC TO ENGINES, MACHINES OR APPARATUS PROVIDED FOR ELSEWHERE; STANDS; SUPPORTS
- F16M11/00—Stands or trestles as supports for apparatus or articles placed thereon ; Stands for scientific apparatus such as gravitational force meters
- F16M11/02—Heads
- F16M11/18—Heads with mechanism for moving the apparatus relatively to the stand
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/203—Drawing of straight lines or curves
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Databases & Information Systems (AREA)
- Biochemistry (AREA)
- Marketing (AREA)
- Analytical Chemistry (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Medicinal Chemistry (AREA)
- Food Science & Technology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Combustion & Propulsion (AREA)
- Development Economics (AREA)
- Mechanical Engineering (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
Abstract
The utility model provides an atmospheric pollution detection device which comprises a mounting seat, a detector, a middle monitoring part, an upper monitoring part and a lower monitoring part, wherein the detector is mounted on the mounting seat and can ascend or descend along the height direction of the mounting seat, and a data processing module is arranged in the detector; the middle monitoring part is arranged on the detector, and the middle monitoring part, the upper monitoring part and the lower monitoring part are all connected with the data processing module; when the detector rises along the height direction of the mounting seat, the upper monitoring part can move to the upper part of the middle monitoring part and the lower monitoring part can move to the lower part of the middle monitoring part; when the detector descends along the height direction of the mounting seat, the upper monitoring part and the lower monitoring part move towards the detector. The utility model also provides an atmospheric pollution trend prediction method. The utility model can realize the effect of simultaneously obtaining a plurality of high atmospheric pollution data and predict the trend of atmospheric pollution based on the data.
Description
[ field of technology ]
The utility model relates to the technical field of atmospheric environment monitoring, in particular to an atmospheric pollution detection device and an atmospheric pollution trend prediction method.
[ background Art ]
With the industrial development, the air pollution problem is increasingly aggravated, the air pollution has serious influence on life and work of people, the air quality is monitored and predicted, alarming is timely carried out, and advanced prevention and treatment are carried out according to the prediction result, so that the pertinence and the effect of the air pollution treatment are improved.
The air pollution detection device is a device commonly used in the prior art for detecting pollutant in the air, and data obtained through the device can help related technicians to realize monitoring of air pollution. For example, chinese patent of public number CN217466834U discloses a "height-adjustable atmospheric pollution control detection device", which comprises a base plate, the upper side wall fixed mounting of bottom plate has first loop bar, the symmetrical sliding connection of the inside wall of first loop bar has first kicking block, the symmetrical fixed mounting of two first kicking blocks is at the lateral wall of second loop bar, the bracing piece runs through the upper side wall of second loop bar and extends to outside, the right side wall fixed mounting of second loop bar has the rack, the upper side wall fixed mounting of bottom plate has the backup pad, the lateral wall of motor output shaft has cup jointed the gear, detect through removing the atmospheric detector to different height, can detect the atmospheric pollution condition of different height positions. However, the above-described device has the following problems when in use: researchers have found that atmospheric pollution is changed from time to time along with the change of various factors of the environment, and when the atmospheric detector is moved to a height to detect and obtain corresponding data, data of other heights cannot be obtained synchronously, which affects the accuracy of the obtained data. Therefore, how to obtain multiple heights of atmospheric pollution data simultaneously is a problem to be solved.
In addition, in the analysis of pollutant concentration data at present, the analysis of future trend of air quality indexes by utilizing various methods such as a traditional physical model, an artificial neural network and the like has become an important direction in the field of atmospheric environment monitoring. In the field of air quality prediction, the existing research is mostly focused on collecting data of various dimensions and various frequencies in a monitoring station, carrying out pretreatment such as interpolation and rejection on the data, substituting the data into a deep neural network for learning training, and rarely preserving original data without damage by someone, wherein the air quality change is a very complex nonlinear process, and the transition arrangement of the original data brings great difficulty to accurately predicting local air quality and environmental pollution treatment. Therefore, providing a method for realizing air pollution trend prediction on the premise of retaining original data is also a problem to be solved.
[ utility model ]
The present utility model is directed to at least solving one of the above-mentioned problems, and provides an air pollution detection device and an air pollution trend prediction method, which can achieve the effect of simultaneously obtaining air pollution data of a plurality of heights.
In order to achieve the above purpose, the technical scheme adopted by the utility model is as follows:
the air pollution detection device comprises a mounting seat, a detector, a middle monitoring part, an upper monitoring part and a lower monitoring part, wherein the detector is mounted on the mounting seat and can ascend or descend along the height direction of the mounting seat, and a data processing module is arranged in the detector; the middle monitoring part is arranged on the detector, and the middle monitoring part, the upper monitoring part and the lower monitoring part are all connected with the data processing module; when the detector ascends along the height direction of the mounting seat, the upper monitoring part can move to the upper side of the middle monitoring part and the lower monitoring part can move to the lower side of the middle monitoring part; when the detector descends along the height direction of the mounting seat, the upper monitoring part and the lower monitoring part move towards the detector.
Further, still include drive division, drive division includes screw motor, guide bar and lifter plate, screw motor install in one side of mount pad and follow the length direction of mount pad extends, the guide bar install in the mount pad corresponds one side of screw motor, the one end spiro union of lifter plate in on the screw motor, the other end of lifter plate cup joint in on the guide bar.
Further, the device also comprises a reverse driving mechanism, wherein the reverse driving mechanism is arranged on the mounting seat and comprises a gear, an upper rack plate and a lower rack plate, the gear is arranged on the mounting seat, the axis of the gear is parallel to the lifting plate, the upper rack plate is connected with the lifting plate, and the upper rack plate is meshed with the gear; the lower rack plate is positioned on one side of the gear, which is away from the upper rack plate, and is meshed with the gear; the upper monitoring part is arranged at one end of the upper rack plate, which is away from the lifting plate, and the lower monitoring part is arranged at one end of the lower rack plate, which is away from the gear.
Further, the reverse driving mechanism further comprises a guide part, the guide part comprises a guide groove, a sliding block and an extension spring, the guide groove is formed in the mounting seat, the guide groove corresponds to the lower rack plate and extends along the length direction of the mounting seat, the sliding block is connected with one end of the lower rack plate, which is away from the gear, and extends into the guide groove, one end of the extension spring is fixed with the top of the mounting seat, which corresponds to the guide groove, and the other end of the extension spring is fixed with the sliding block.
Further, the air pollution detection device further comprises a solar power supply assembly, the solar power supply assembly comprises a solar charging plate, a charging controller and a storage battery pack, the solar charging plate is arranged on the front side of the mounting seat, the charging controller is arranged inside the mounting seat and is connected with the solar charging plate, the storage battery pack is arranged on the mounting seat and is connected with the charging controller, and the storage battery pack is connected with the screw motor.
An atmospheric pollution trend prediction method comprises the following steps:
s1, acquiring historical atmospheric pollution data recorded from the data processing module;
s2, performing basic surface pretreatment and initial classification on the historical meteorological data and the pollutant concentration data to obtain candleholder diagrams containing trend reversal signals in a unit of day, wherein the number of the candleholder diagrams containing the trend reversal signals is a plurality of;
s3, sorting a plurality of candlestick images containing trend reversal signals into a K line image library;
s4, constructing a pollution trend model based on a one-dimensional convolutional neural network CNN network;
s5, inputting the K line graph library into the pollution trend model for training to obtain a trained pollution trend model;
and S6, sending the atmospheric pollution data tensor into the trained pollution trend model for prediction, and obtaining a trend judgment result of atmospheric pollution.
Further, the basic surface preprocessing in step S2 is as follows:
aiming at the extreme value of the historical atmospheric pollution data, adopting median extremum removal processing;
aiming at the missing value of the historical atmospheric pollution data, adopting average value filling to process partial missing data, and directly deleting the missing data all the day;
z-score normalization was performed on the processed data:
assuming factor values of x1, x2, x3, xn transforms these values as follows:
the newly converted sequence value will be a standard sequence with 0 as the mean and 1 as the variance, transformed by the formula.
Further, in step S2:
and after the pollutant concentration data are processed, drawing a common candlestick chart, and then carrying out concentration marking on the common candlestick chart to obtain the candlestick chart containing the trend reversing signal.
Further, in step S2: the concentration labeling is performed by concentration matching.
Further, the historical atmospheric pollution data includes average values of the atmospheric pollution data of different heights respectively monitored by the middle monitoring part, the upper monitoring part and the lower monitoring part.
By adopting the technical scheme, the utility model has the following beneficial effects:
when the air pollution detection device is used, when the detector ascends along the height direction of the mounting seat, the upper monitoring part can move to the upper part of the middle monitoring part, and the lower monitoring part can move to the lower part of the middle monitoring part, so that air pollution data can be obtained through the upper monitoring part, the middle monitoring part and the lower monitoring part with different heights.
[ description of the drawings ]
FIG. 1 is a schematic diagram of an air pollution detection device according to the present utility model.
Fig. 2 is a schematic view of the back drive mechanism of fig. 1.
FIG. 3 is a schematic view of the installation of the lower rack plate and the mounting base.
FIG. 4 is a flowchart of an air pollution trend prediction method in the second embodiment.
In the drawings, a 1-mounting seat, a 11-wall-mounted rod, a 12-mounting groove, a 13-mounting step, a 2-detector, a 3-middle monitoring part, a 4-upper monitoring part, a 5-lower monitoring part, a 61-screw motor, a 62-lifting plate, a 71-gear, a 72-upper rack plate, a 73-lower rack plate, a 74-guide groove, a 75-sliding block, a 76-extension spring, a 81-solar charging plate, a 82-storage battery pack and a 83-charging controller.
[ detailed description ] of the utility model
The following description of the embodiments of the present utility model will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present utility model, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the utility model without making any inventive effort, are intended to be within the scope of the utility model.
It will be understood that when an element is referred to as being "fixed to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "disposed on" another element, it can be directly on the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this utility model belongs. The terminology used in the description of the utility model herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the utility model. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Embodiment one:
as shown in fig. 1 and 2, a first embodiment of the present utility model provides an air pollution detection device, which includes a mounting base 1, a detector 2, a middle monitoring portion 3, an upper monitoring portion 4, and a lower monitoring portion 5. The detector 2 adopts an air pollution monitor in the prior art, the detector 2 is arranged on the mounting seat 1, the detector 2 can ascend or descend along the height direction of the mounting seat 1, and a data processing module is arranged in the detector 2; the middle monitoring part 3 is arranged on the detector 2, and the middle monitoring part 3, the upper monitoring part 4 and the lower monitoring part 5 are all connected with the data processing module; when the detector 2 rises in the height direction of the mount 1, the upper monitoring portion 4 can move above the middle monitoring portion 3 and the lower monitoring portion 5 can move below the middle monitoring portion 3; when the detector 2 descends in the height direction of the mounting base 1, both the upper monitor portion 4 and the lower monitor portion 5 move toward the detector 2. The middle monitoring part 3, the upper monitoring part 4 and the lower monitoring part 5 all adopt microclimate instruments.
When the above-mentioned air pollution detection device is used, when the detector 2 rises along the height direction of the mounting seat 1, the upper monitoring part 4 can move to the upper side of the middle monitoring part 3 and the lower monitoring part 5 can move to the lower side of the middle monitoring part 3, so that air pollution data can be obtained through the upper monitoring part 4, the middle monitoring part 3 and the lower monitoring part 5 with different heights, and the effect of simultaneously obtaining a plurality of air pollution data with different heights can be realized.
In this embodiment, a plurality of wall-mounted posts 11 are disposed at intervals at the bottom of the mounting base 1, and the wall-mounted posts 11 are L-shaped, so that the mounting base 1 is fixed at a high place by fixing the wall-mounted posts 11 to the outside of a building.
In the present embodiment, the air pollution detection device further includes a driving unit including a screw motor 61, a guide rod, and a lifting plate 62. The screw motor 61 is installed on one side of the mounting seat 1 and extends along the length direction of the mounting seat 1, and the guide rod is installed on one side of the mounting seat 1 corresponding to the screw motor 61. One end of the lifting plate 62 is screwed to the screw motor 61, and in detail, one end of the lifting plate 62 is screwed to the screw of the screw motor 61. The other end of the lifting plate 62 is sleeved on the guide rod. The screw motor 61 drives the screw to rotate, and the lifting plate 62 can reciprocate along the longitudinal direction of the mount 1.
In the present embodiment, the present utility model further includes a back driving mechanism, and the back driving mechanism is mounted on the mounting base 1. The back drive mechanism includes a gear 71, an upper rack plate 72, and a lower rack plate 73. The gear 71 is mounted on the mounting base 1 and the axis of the gear 71 is parallel to the lifter plate 62. The upper rack plate 72 is connected to the lifting plate 62 and the upper rack plate 72 is engaged with the gear 71, specifically, the lower end of the upper rack plate 72 is connected to the lifting plate 62. The lower rack plate 73 is located on the side of the gear 71 facing away from the upper rack plate 72 and is in mesh with the gear 71, in particular the lower rack plate 73 is connected to the mounting seat 1. The upper monitoring portion 4 is mounted on the end of the upper rack plate 72 facing away from the lifting plate 62, and the lower monitoring portion 5 is mounted on the end of the lower rack plate 73 facing away from the gear 71.
When the lifting plate 62 moves upward along the length direction of the mounting seat 1, the lifting plate 62 drives the upper rack plate 72 to move upward, so that the upper monitoring portion 4 can move to the upper side of the middle monitoring portion 3. The gear 71 is driven to rotate during the upward movement of the upper rack plate 72, and the gear 71 drives the lower rack plate 73 to extend towards the lower side of the lifting plate 62, so that the lower monitoring portion 5 moves to the lower side of the middle monitoring portion 3, at this time, the heights of the middle monitoring portion 3 and the upper monitoring portion 4 are both increased, and the lower monitoring portion 5 can move to a lower level than the middle monitoring portion 3 to acquire data of atmospheric pollution. When the lifting plate 62 drives the upper rack plate 72 to move downwards, the upper rack plate 72 and the lower monitoring portion 5 can both be recovered towards the lifting plate 62, and when strong weather, such as strong wind and strong rain, is encountered, a user can make the upper rack plate 72 and the lower rack plate 73 both be recovered towards the lifting plate 62, so that the influence of strong wind and strong rain on the whole structural stability can be reduced.
In this embodiment, the back driving mechanism further includes a guide portion, the guide portion includes a guide groove 74, a sliding block 75 and an extension spring 76, the guide groove 74 is provided on the mount 1, the guide groove 74 corresponds to the lower rack plate 73 and extends along the length direction of the mount 1, the sliding block 75 is connected to one end of the lower rack plate 73, which is away from the gear 71, and extends into the guide groove 74, one end of the extension spring 76 is fixed to the top of the guide groove 74 corresponding to the mount 1, and the other end of the extension spring 76 is fixed to the sliding block 75. The arrangement of the guide groove 74, the slide block 75, and the tension spring 76 can increase the stability of the lower rack plate 73 in the up-and-down movement process of the lower rack plate 73. In addition, the lifting plate 62 and the mounting seat 1 can form a limiting space, and the lower rack plate 73 is limited in the limiting space, so that larger displacement relative to the mounting seat 1 in the process of moving the lower rack plate 73 up and down is avoided.
In this embodiment, the air pollution detection device further includes a solar power supply assembly, and the solar power supply assembly includes a solar charging panel 81, a charging controller 83, and a storage battery 82. The solar charging plate 81 is disposed on the front side of the mounting seat 1, specifically, the mounting seat 1 is concavely provided with a mounting groove 12, two opposite sides of the mounting groove 12 are provided with mounting steps 13, the mounting steps 13 are provided with sliding grooves along the length direction, two opposite ends of the lifting plate 62 slidingly extend into corresponding sliding grooves, and a screw of the screw motor 61 is disposed in one of the sliding grooves; the front sides of the two mounting steps 13 are provided with embedded grooves, and a solar charging plate 81 is fixed in one embedded groove. The charging controller 83 is installed inside the installation seat 1, the charging controller 83 is connected with the solar charging panel 81, the storage battery 82 is installed on the installation seat 1 and connected with the charging controller 83, and specifically, the charging controller 83 and the storage battery 82 are all installed in the inner wall corresponding to the installation groove 12. The battery pack 82 is connected to the screw motor 61. The solar charging panel 81 charges the storage battery 82 through the charging controller 83, and the electricity of the storage battery 82 is used for the screw motor 61 to work. Since the upper rack plate 72 and the lower rack plate 73 are recovered only under strong wind and strong rain under normal conditions, the amount of electricity of the battery pack 82 after long-time charging is sufficient for normal operation of the screw motor 61.
Embodiment two:
as shown in fig. 1 to 4, a second embodiment of the present utility model provides an air pollution tendency prediction method, which includes the steps of:
s1, acquiring historical atmospheric pollution data recorded from a data processing module;
s2, performing basic surface pretreatment and initial classification on historical meteorological data and pollutant concentration data to obtain candlestick images containing trend inversion signals in a unit of day, wherein the number of the candlestick images containing the trend inversion signals is a plurality of;
s3, sorting a plurality of candlestick images containing trend reversal signals into a K line image library;
s4, constructing a pollution trend model based on a one-dimensional convolutional neural network CNN network;
s5, inputting the K line graph library into a pollution trend model for training to obtain a trained pollution trend model;
and S6, sending the atmospheric pollution data tensor into a trained pollution trend model to predict, and obtaining a trend judgment result of atmospheric pollution.
In the embodiment, the historical atmospheric pollution data adopts the monitoring data of an on-line monitoring station of the atmospheric quality of cassia Lin Shi, and the data stored in the database are pollutant and meteorological data corresponding to the corresponding station through the atmospheric pollution detection device once every five minutes. The meteorological data comprise atmospheric pressure, rainfall, wind speed, wind direction, humidity, temperature and the like. The pollutant concentration data includes NO2, SO2, CO, O3, PM2.5, PM10, etc. The data time window is selected from 8.8.2017 to 8.8.2019. The historical air pollution data specifically includes average values of air pollution data of different heights monitored by the middle monitoring part 3, the upper monitoring part 4 and the lower monitoring part 5.
In the present embodiment, the basic surface preprocessing in step S2 is:
aiming at extreme values of historical atmospheric pollution data, adopting median extremum removal processing;
aiming at the missing value of the historical atmospheric pollution data, filling and processing the partial missing data by adopting an average value, and directly deleting the missing data all the day;
z-score normalization was performed on the processed data:
assuming factor values of x1, x2, x3, xn transforms these values as follows:
the new converted sequence value will be a standard sequence with 0 as the mean and 1 as the variance, converted according to equation 3.
In the present embodiment, in step S2:
after the pollutant concentration data are processed, a common candlestick chart is drawn, and then concentration marks are carried out on the common candlestick chart, so that the candlestick chart containing a trend reversing signal is obtained. Specific:
the feature vector PCF of the candlestick chart of the concentration of the contaminant: five different meaningful features are extracted from the candlestick chart to reflect the overall concentration condition of one day, namely a category feature C Shape, an entity feature EntityLEN, an upper hatching feature Upperhatch LEN, a lower hatching feature UndercutLEN, a Change rate feature R Change and the like. Then, the candleholder feature vector on day i is expressed as: pcfi= < C Shape, entityLEN, upperhatchLEN, upperhatchLEN, RChange >, for convenience of recording, the feature vector is abbreviated as: pcfi= < fi1, fi2, fi5>
Wherein:
class feature C Shape, wherein C Shape e {1, 2..12 }, is defined as twelve different shapes by distinguishing the rise and fall of density, the presence of real entities, the presence of upper and lower hatching.
The entity signature EntityLEN, in the candleholder diagram, the length of the entity characterizes the intensity of the increase/decrease in contaminant concentration. Longer physical candelabrus symbolize a significant trend of increase/decrease.
The upper hatched feature UpperhatchLEN, most of the trend turning points, are determined by this feature. The obvious rules that this feature exhibits are: a concentration candleholder plot with a longer upper hatching indicates that the intensity of the concentration trend drop is severe and even more likely to continue to drop during the next time interval. Uppersatchlen=high i -max(OPEN i -CLOSE i )。
Under-hatched feature underhatched len, also, a concentration candleholder graph with longer under-hatched indicates that the signal of the concentration trend rise is strong, which may lead to an increase in the concentration later, underhatched len=min (OPENi-close) -LOW i 。
The Change rate characteristic R Change is used for calculating information of average pressure Change trend through comparison of two candleholder diagrams at adjacent positions so as to lock a pollutant concentration mode which is useful at the current moment. The overall concentration level was characterized by the average concentration variation throughout the day and was taken as the center of the concentration candlestick. This feature will be described by the Change in concentration level from day to day, i.e. R Change = AVG i -AVG i-1 。
By analyzing these candleholders with concentration trend signals, trend reversal signals can be found, i.e. candleholders containing trend reversal signals are formed.
In the present embodiment, in step S2: the concentration marking is performed by concentration matching, specifically:
concentration increasing/decreasing period at successive time intervals t 1 ,t 2 ,t 3 ,...t i ,C i,avg In (1), if Ci, avg>max (Ci-1, avg, ci, avg) i=1, 2. If Ci, avg<min (Ci-1, avg, ci, avg) i=1, 2. For example, ci1, avg, ci3, avg are two nearest neighboring concentration valleys, ci2, avg is the concentration peak between them, and i1<i2<i3, the continuous time interval between the concentration valley Ci1, avg and the next concentration peak Ci2, avg is regarded as a concentration increasing period, and the continuous time interval between the concentration valley Ci2, avg and the next concentration peak Ci3, avg is regarded as a concentration decreasing period.
Concentration pattern, concentration pattern M is a sequence consisting of concentration candlestick feature vectors, denoted as m= < PCF1,..pcfk >, where K is the length of the concentration period in each period of concentration increase or decrease. For the pattern m1= < PCF1,..pcfk > and m2= < PCF1,..pcfk >, in view of the fact that the most recent candlestick shape can provide more useful information for future predictions, matching is performed in reverse order from back to front, if there are ρ sets of parameters in the K sets of features that can complete matching, the parameter ρ is defined as the matching rate. And the matching rate of the feature vectors of the two candelabrus is measured by the distance, and if the matching rate is lower than a certain threshold value, the matching is considered to be successful. The distance formula is defined as:
where w1, w5 is a weight factor, and the sum is 1, the value of the weight in this study was determined by using the analytical hierarchy algorithm AHP. The candleholder graph closest to the current day can describe more useful information, so the corresponding weight w1 will be given the highest value. For the category characteristic C Shape, the matching accuracy is required to be the highest, so the calculation formula is as follows:
for four characteristics of an entity, an upper hatching, a lower hatching and a change rate, the corresponding forehead characteristic values are all mapped into the interval of [0,1] in a normalized data processing mode, and the calculation formula is as follows:
D(f ij ，f′ ij )＝|f ij -f′ ij i, j=2, …,5, formula 6
In a single candlestick chart, the prediction method of the atmospheric pollution concentration by adopting the candlestick chart comprises the following steps:
during diffusion of atmospheric contaminants, excavation forms two distinct sets of contaminant concentration patterns: a concentration increasing pattern set and a concentration decreasing pattern set. The next concentration change level is predicted by observing the concentration candlestick chart over time period n. If the candleholder pattern to be predicted does not reverse the shape of the candleholder and there is no significant indication of pressure reversal during diffusion of contaminant concentrations, then it is assumed that the predicted result will remain unchanged from the previous state. Otherwise, pattern matching will be performed to determine whether the trend will be reversed. Backtracking to the concentration peak or concentration valley nearest to the current time will form a concentration pattern of n-k+1 durations: m1= < PCFk, >, PCFn >.
According to the pattern currently formed, the pattern is placed in a concentration pattern set which is generated for searching and matching. The current pattern sequence M1 may match either the corresponding pattern Mk or a subsequence of Mk. Because of the huge data set and the complex distance calculation process, the positioning process is time consuming, and therefore, an index is created for each concentration pattern, and the pattern matching process is expedited by marking the position of the candleholder pattern with the inversion signal in each pattern. The sub-sequence of N-k+1 is truncated forward as newly generated n2= < PCFi-n+k, PCFi >, according to the index position, and then M1 and N2 continue to be matched.
After successful contaminant concentration pattern matching, the corresponding next average concentration level is recorded. If a plurality of modes can be matched at the same time, a voting mechanism is adopted, and the majority is used as a corresponding prediction result. If the current concentration pattern cannot be matched in the pattern set, the subsequent concentration change level is inferred from the intensity of the inversion signal exhibited by the candleholder plots formed over the past n days. If the current pattern length is too long, already greater than the maximum length of all patterns in the pattern set, and the average concentration level is relatively high or low, then it is determined that the current concentration trend is more likely to transition.
In this embodiment, the specific method of step S3 is as follows: drawing by using Matlab programming software, firstly drawing a concentration jump interval, namely the highest concentration and the lowest concentration of each day, then drawing a candlestick chart around the concentration interval, and distinguishing by color filling: the candleholder picture is filled with red if the ending value of the day is higher than the starting value and green if the ending value of the day is lower than the starting value. Wherein the area between the start value and the end value is called the solid, the line between the highest concentration level and the border above the solid is the upper hatching, and the line between the lowest pressure level and the border below the solid is the lower hatching.
In this embodiment, the specific methods of steps S4 to S6 are well known to those skilled in the art, for example, a rolling bearing state monitoring method and system based on a convolutional neural network model disclosed in chinese patent application with publication No. CN111060316a, a PM2.5 concentration prediction method, device and medium disclosed in chinese patent application with publication No. CN109978228A, an oil pumping well fault diagnosis method based on a characteristic recalibration residual convolutional neural network disclosed in chinese patent application with publication No. CN111810124A, etc., so the specific method of step S4 is not described herein again.
To verify the accuracy of the method, three reference models were built to evaluate the performance of the proposed method, namely a time series model, a logistic regression model logistic regression model model, and a support vector machine Support Vector Machine model. The processed data are trained through a convolutional neural network model, a time sequence model, a logistic regression model and a support vector machine model respectively. A total of 7000 concentration patterns were acquired in the dataset, 70% of which was used as training dataset and 30% was used for testing. For control variables, 50 epochs were taken as training batches for each network and the average error was used as a model evaluation index.
Experimental results show that compared with other models, the convolutional neural network model based on the K line graph achieves the highest accuracy, the error is 15.31%, and the error is 32.81% when the convolutional neural network model based on the time sequence is simple. Therefore, the accuracy of the pattern matching extraction characteristic network model based on the K line graph is obviously higher than that of the common time sequence. The K line graph is applied to the field of atmospheric pollutant analysis, so that data information can be completely stored, and local change information of a pollutant concentration change process in an atmospheric pollutant diffusion process can be fully extracted, so that guidance is provided for trend change. To further illustrate the method and technical effects of the present embodiment, one skilled in the art can refer to the following documents: PM based on candlestick pattern matching 2.5 Extraction of diffusion characteristics [ J/OL]It was published in computer applications at day 14, 7, 2022。
In addition, since the present embodiment combines the data detected by the air pollution detection device in the first embodiment, the accuracy of predicting the trend is increased. In practical use of the method in this embodiment, the historical atmospheric pollution data may not be limited to the average values of the atmospheric pollution data of different heights monitored by the middle monitoring portion 3, the upper monitoring portion 4, and the lower monitoring portion 5 in this embodiment, and in order to adapt to the atmospheric pollution prediction of different heights, a person skilled in the art may select any one of the data of the middle monitoring portion 3, the upper monitoring portion 4, and the lower monitoring portion 5 to perform the atmospheric pollution prediction, so as to increase flexibility and pertinence of the atmospheric pollution prediction.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing description is directed to the preferred embodiments of the present utility model, but the embodiments are not intended to limit the scope of the utility model, and all equivalent changes or modifications made under the technical spirit of the present utility model should be construed to fall within the scope of the present utility model.
Claims (10)
1. An atmospheric pollution detection device, its characterized in that: the device comprises a mounting seat (1), a detector (2), a middle monitoring part (3), an upper monitoring part (4) and a lower monitoring part (5), wherein the detector (2) is mounted on the mounting seat (1) and can ascend or descend along the height direction of the mounting seat (1), and a data processing module is arranged in the detector (2); the middle monitoring part (3) is arranged on the detector (2), and the middle monitoring part (3), the upper monitoring part (4) and the lower monitoring part (5) are all connected with the data processing module; when the detector (2) rises along the height direction of the mounting seat (1), the upper monitoring part (4) can move to the upper part of the middle monitoring part (3) and the lower monitoring part (5) can move to the lower part of the middle monitoring part (3); when the detector (2) descends along the height direction of the mounting seat (1), the upper monitoring part (4) and the lower monitoring part (5) move towards the detector (2).
2. An atmospheric pollution detection device as defined in claim 1, wherein: still include drive division, drive division includes screw motor (61), guide bar and lifter plate (62), screw motor (61) install in one side of mount pad (1) and follow the length direction of mount pad (1) extends, the guide bar install in mount pad (1) correspond one side of screw motor (61), the one end spiro union of lifter plate (62) in on screw motor (61), the other end of lifter plate (62) cup joint in on the guide bar.
3. An atmospheric pollution detection device as defined in claim 2, wherein: the device comprises a mounting seat (1), and is characterized by further comprising a back driving mechanism, wherein the back driving mechanism is arranged on the mounting seat (1) and comprises a gear (71), an upper rack plate (72) and a lower rack plate (73), the gear (71) is arranged on the mounting seat (1) and the axis of the gear (71) is parallel to the lifting plate (62), the upper rack plate (72) is connected with the lifting plate (62) and the upper rack plate (72) is meshed with the gear (71); the lower rack plate (73) is positioned on the side of the gear (71) away from the upper rack plate (72) and is meshed with the gear (71); the upper monitoring part (4) is arranged at one end of the upper rack plate (72) deviating from the lifting plate (62), and the lower monitoring part (5) is arranged at one end of the lower rack plate (73) deviating from the gear (71).
4. An atmospheric pollution detection device as defined in claim 3, wherein: the reversing drive mechanism further comprises a guide part, the guide part comprises a guide groove (74), a sliding block (75) and a tension spring (76), the guide groove (74) is formed in the mounting seat (1), the guide groove (74) corresponds to the lower rack plate (73) and extends along the length direction of the mounting seat (1), the sliding block (75) is connected with one end, deviating from the gear (71), of the lower rack plate (73) and extends into the guide groove (74), one end of the tension spring (76) is fixed with the top of the guide groove (74) corresponding to the mounting seat (1), and the other end of the tension spring (76) is fixed with the sliding block (75).
5. An atmospheric pollution detection device as defined in claim 2, wherein: the air pollution detection device further comprises a solar power supply assembly, the solar power supply assembly comprises a solar charging plate (81), a charging controller (83) and a storage battery (82), the solar charging plate (81) is arranged on the front side of the mounting seat (1), the charging controller (83) is arranged inside the mounting seat (1) and is connected with the solar charging plate (81), and the storage battery (82) is arranged on the mounting seat (1) and is connected with the charging controller (83), and the storage battery (82) is connected with the screw motor (61).
6. An atmospheric pollution trend prediction method is characterized by comprising the following steps:
s1, acquiring historical atmospheric pollution data recorded from the data processing module;
s2, performing basic surface pretreatment and initial classification on the historical meteorological data and the pollutant concentration data to obtain candleholder diagrams containing trend reversal signals in a unit of day, wherein the number of the candleholder diagrams containing the trend reversal signals is a plurality of;
s3, sorting a plurality of candlestick images containing trend reversal signals into a K line image library;
s4, constructing a pollution trend model based on a one-dimensional convolutional neural network CNN network;
s5, inputting the K line graph library into the pollution trend model for training to obtain a trained pollution trend model;
and S6, sending the atmospheric pollution data tensor into the trained pollution trend model for prediction, and obtaining a trend judgment result of atmospheric pollution.
7. The method according to claim 6, wherein the basic surface pretreatment in step S2 is as follows:
aiming at the extreme value of the historical atmospheric pollution data, adopting median extremum removal processing;
aiming at the missing value of the historical atmospheric pollution data, adopting average value filling to process partial missing data, and directly deleting the missing data all the day;
z-score normalization was performed on the processed data:
assume that the factor values are x1, x2, x3..
The new converted sequence value will be a standard sequence with 0 as the mean and 1 as the variance, converted according to equation (3).
8. The air pollution tendency prediction method according to claim 7, wherein in step S2:
and after the pollutant concentration data are processed, drawing a common candlestick chart, and then carrying out concentration marking on the common candlestick chart to obtain the candlestick chart containing the trend reversing signal.
9. The air pollution tendency prediction method according to claim 7, wherein in step S2: the concentration labeling is performed by concentration matching.
10. The method for predicting the atmospheric pollution tendencies of claim 7 wherein: the historical atmospheric pollution data comprise average values of the atmospheric pollution data of different heights, which are respectively monitored by the middle monitoring part (3), the upper monitoring part (4) and the lower monitoring part (5).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311256930.9A CN117330710A (en) | 2023-09-26 | 2023-09-26 | Atmospheric pollution detection device and atmospheric pollution trend prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311256930.9A CN117330710A (en) | 2023-09-26 | 2023-09-26 | Atmospheric pollution detection device and atmospheric pollution trend prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117330710A true CN117330710A (en) | 2024-01-02 |
Family
ID=89278354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311256930.9A Pending CN117330710A (en) | 2023-09-26 | 2023-09-26 | Atmospheric pollution detection device and atmospheric pollution trend prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117330710A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111854840A (en) * | 2020-07-29 | 2020-10-30 | 武汉城市职业学院 | Indoor self-propelled environment detection equipment |
| CN211978814U (en) * | 2020-03-09 | 2020-11-20 | 山西福万达工业新材料有限公司 | Monitoring equipment for atmospheric pollution treatment |
| WO2021051609A1 (en) * | 2019-09-20 | 2021-03-25 | 平安科技（深圳）有限公司 | Method and apparatus for predicting fine particulate matter pollution level, and computer device |
| CN113252091A (en) * | 2021-05-19 | 2021-08-13 | 张锦灵 | On-spot data acquisition device based on geological environment monitoring |
| CN215297286U (en) * | 2020-12-11 | 2021-12-24 | 郑州力帆电气有限公司 | A equipment for air pollution detects |
| CN215865319U (en) * | 2021-08-30 | 2022-02-18 | 玉林师范学院 | Growth environment monitoring devices is planted in land for growing field crops |
| CN115372566A (en) * | 2022-09-23 | 2022-11-22 | 国网湖北省电力有限公司中超建设管理公司 | Gas monitor and use method thereof |
| CN116665798A (en) * | 2023-04-27 | 2023-08-29 | 海南大学 | Air pollution trend early warning method and related device |
-
2023
- 2023-09-26 CN CN202311256930.9A patent/CN117330710A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021051609A1 (en) * | 2019-09-20 | 2021-03-25 | 平安科技（深圳）有限公司 | Method and apparatus for predicting fine particulate matter pollution level, and computer device |
| CN211978814U (en) * | 2020-03-09 | 2020-11-20 | 山西福万达工业新材料有限公司 | Monitoring equipment for atmospheric pollution treatment |
| CN111854840A (en) * | 2020-07-29 | 2020-10-30 | 武汉城市职业学院 | Indoor self-propelled environment detection equipment |
| CN215297286U (en) * | 2020-12-11 | 2021-12-24 | 郑州力帆电气有限公司 | A equipment for air pollution detects |
| CN113252091A (en) * | 2021-05-19 | 2021-08-13 | 张锦灵 | On-spot data acquisition device based on geological environment monitoring |
| CN215865319U (en) * | 2021-08-30 | 2022-02-18 | 玉林师范学院 | Growth environment monitoring devices is planted in land for growing field crops |
| CN115372566A (en) * | 2022-09-23 | 2022-11-22 | 国网湖北省电力有限公司中超建设管理公司 | Gas monitor and use method thereof |
| CN116665798A (en) * | 2023-04-27 | 2023-08-29 | 海南大学 | Air pollution trend early warning method and related device |
Non-Patent Citations (1)
| Title |
|---|
| 许睿等: "基于烛台图模式匹配的PM2.5扩散特征的提取", 《计算机应用》, vol. 43, no. 5, 10 May 2023 (2023-05-10), pages 1394 - 1400 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109063366B (en) | Building performance data online preprocessing method based on time and space weighting | |
| CN107451600B (en) | Online photovoltaic hot spot fault detection method based on isolation mechanism | |
| CN106779200A (en) | Based on the Wind turbines trend prediction method for carrying out similarity in the historical data | |
| CN111429415B (en) | Method for constructing efficient detection model of product surface defects based on network collaborative pruning | |
| CN112785066B (en) | Global wild fire season space-time prediction method based on convolution-recurrent neural network | |
| CN110555551B (en) | Air quality big data management method and system for smart city | |
| CN115809405A (en) | Fan main shaft gear box temperature anomaly detection method based on multi-feature fusion | |
| CN112347927B (en) | High-resolution image building extraction method based on convolutional neural network probability decision fusion | |
| CN108491580A (en) | A kind of equipment fault diagnosis apparatus and system | |
| CN108615011A (en) | Non- trimming video behavior identification prediction method based on multi-scale sliding window mouth | |
| CN114841250A (en) | Industrial system production abnormity detection and diagnosis method based on multi-dimensional sensing data | |
| CN117131110B (en) | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis | |
| CN111274912B (en) | Working condition early warning method for sucker-rod pump based on noise reduction indicator diagram | |
| CN117330710A (en) | Atmospheric pollution detection device and atmospheric pollution trend prediction method | |
| TW202119298A (en) | Solar panel power system abnormal diagnosis and analysis device and method based on fhmm (factorial hidden markov model) and power generation prediction | |
| CN111460027B (en) | Intelligent dynamic monitoring method and system suitable for energy Internet | |
| CN117370813A (en) | Atmospheric pollution deep learning prediction method based on K line pattern matching algorithm | |
| CN112488119A (en) | Tunnel block falling or water seepage detection and measurement method based on double-depth learning model | |
| CN117033923A (en) | Method and system for predicting crime quantity based on interpretable machine learning | |
| CN115527151B (en) | Video anomaly detection method, system, electronic equipment and storage medium | |
| CN117009900A (en) | Internet of things signal anomaly detection method and system based on graph neural network | |
| CN109598933A (en) | It is a kind of based on the k of data-driven adjacent to the traffic flow forecasting method of non parametric regression | |
| CN113607710B (en) | Method for on-line monitoring water quality and device and system applied by same | |
| CN114065335A (en) | Building energy consumption prediction method based on multi-scale convolution cyclic neural network | |
| CN111625525A (en) | Environmental data repairing/filling method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |