CN114581278A - Atmospheric pollutant tracing and troubleshooting method, terminal and system based on intelligent street lamp - Google Patents
Atmospheric pollutant tracing and troubleshooting method, terminal and system based on intelligent street lamp Download PDFInfo
- Publication number
- CN114581278A CN114581278A CN202210208991.7A CN202210208991A CN114581278A CN 114581278 A CN114581278 A CN 114581278A CN 202210208991 A CN202210208991 A CN 202210208991A CN 114581278 A CN114581278 A CN 114581278A
- Authority
- CN
- China
- Prior art keywords
- data
- intelligent
- atmospheric
- sub
- tracing
- 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
- 239000003344 environmental pollutant Substances 0.000 title claims abstract description 73
- 231100000719 pollutant Toxicity 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000013024 troubleshooting Methods 0.000 title claims abstract description 7
- 238000001514 detection method Methods 0.000 claims abstract description 22
- 238000004891 communication Methods 0.000 claims abstract description 11
- 238000012800 visualization Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 30
- 238000013135 deep learning Methods 0.000 claims description 25
- 238000012937 correction Methods 0.000 claims description 22
- 238000011835 investigation Methods 0.000 claims description 19
- 238000013527 convolutional neural network Methods 0.000 claims description 17
- 238000009792 diffusion process Methods 0.000 claims description 14
- 238000007689 inspection Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 230000003993 interaction Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 7
- 230000002093 peripheral effect Effects 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000000356 contaminant Substances 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 238000013499 data model Methods 0.000 claims description 3
- 238000001556 precipitation Methods 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 abstract description 5
- 230000001360 synchronised effect Effects 0.000 abstract description 5
- 238000012821 model calculation Methods 0.000 abstract description 4
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 239000000126 substance Substances 0.000 abstract description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 2
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 239000000463 material Substances 0.000 abstract description 2
- 238000003915 air pollution Methods 0.000 abstract 1
- 230000000007 visual effect Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
Images
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
- 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
- G01N33/0031—General constructional details of gas analysers, e.g. portable test equipment concerning the detector comprising two or more sensors, e.g. a sensor array
- G01N33/0034—General constructional details of gas analysers, e.g. portable test equipment concerning the detector comprising two or more sensors, e.g. a sensor array comprising neural networks or related mathematical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Development Economics (AREA)
- Molecular Biology (AREA)
- Marketing (AREA)
- Pathology (AREA)
- Computational Linguistics (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Combustion & Propulsion (AREA)
- Biomedical Technology (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
Abstract
The invention discloses an atmospheric pollutant tracing and troubleshooting method, terminal and system based on an intelligent street lamp. The intelligent lamp pole sensing module comprises various sensors and is used for collecting air pollution sensing information of the coupled longitude and latitude coordinates; the 5G transmission module comprises a communication base station, a synchronous clock source and an intelligent gateway, wherein the communication base station, the synchronous clock source and the intelligent gateway are arranged on the intelligent lamp pole and are used for transmitting the atmospheric pollution sensing information and the longitude and latitude coordinate information of the unified timestamp; the model calculation module is used for constructing a basic wind field model; fitting a pollutant range model through the monitoring data; calculating a pollutant diffusion center; and the GIS visualization platform is used for visually outputting the three-dimensional position of the pollution source. The automatic detection algorithm can be used for environment detection of different places such as chemical industry parks, communities and the like. Can fix a position the pollutant fast, practice thrift manpower and materials, guarantee environmental safety.
Description
Technical Field
The invention belongs to the field of environment monitoring devices, and particularly relates to an atmospheric pollutant tracing and inspection method, terminal and system based on an intelligent street lamp.
Background
Because a large amount of common people are arranged near the places such as the chemical industry park, the park and the community, the emergency evacuation is needed when an accident occurs, the high requirement on the instant environment information is met when the accident is handled, and the detection by using a more flexible and efficient device and technology instead of manual work is deeply integrated to probe the important problem to be solved urgently.
Most of the existing pollutant detection systems depend on manpower, and most of the existing intelligent street lamps only have the detection of PM2.5 and other atmospheric pollutants. The existing rescue robot has more perfect functions, but still needs to sense the rescue environment in advance, and the functions are single.
In summary, the prior art has certain defects and inconveniences in the above usage scenarios, so it is necessary to improve the above usage scenarios.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the atmospheric pollutant tracing and inspection method based on the intelligent street lamp solves the problems of single function, low speed and low efficiency of a regional atmospheric pollution detection technology in the prior art.
The invention adopts the following technical scheme for solving the technical problems:
an atmospheric pollutant tracing and inspection method based on an intelligent street lamp comprises the following steps:
step 1, acquiring various sensor data around each intelligent lamp pole by applying a sensing module arranged on the intelligent lamp pole, giving a timestamp and a position stamp to the sensor data, and constructing a distributed sensing network based on the intelligent lamp pole;
step 2, constructing an original convolution neural network model for each intelligent lamp pole, and performing deep learning on the convolution neural network models of the respective lamp poles by combining the data of the sensors of the intelligent lamp poles;
step 3, applying a Gaussian correction model based on deep learning to predict sensor data of a neighbor smart lamp pole, and acquiring and outputting prediction information of peripheral atmospheric concentration and pollution sources;
step 4, updating the training weight of the convolutional neural network model according to the data value of the neighbor sensor, training the convolutional neural network model by using the current sensor data of the neighbor sensor, and updating the internal parameters of the Gaussian correction model based on deep learning;
and 5, repeatedly executing the step 3 to the step 4.
The sensor data includes, but is not limited to, location, time, wind speed, wind direction, precipitation, air humidity, various pollutant concentrations.
The deep learning-based Gaussian correction model is specifically represented as follows:
Ri＝(b,Vi,Cij) Wherein R isiFor intelligent lamp post DiRelative distance from the center of diffusion of the contaminant, b ═ Vi,HiAnd f) is the internal parameter of the Gaussian correction model based on deep learning, ViFor intelligent lamp post DiDetected wind speed, HiFor intelligent lamp post DiDetected humidity, f is whether rainfall is present, CijFor intelligent lamp post DiAnd (4) detecting the concentration of the j pollutant, wherein i and j are positive integers.
The pollutant discharge amount Q per unit time is calculated according to the following formula:
Q＝2πCij*V*σy*σz/{e^(-y2/2σy 2)*{e^[-(z-H)2/2σy 2]+e^[-(z+H)2/2σz 2]}}
wherein V is the discharge port is flatMean wind speed, σyIs the lateral diffusion coefficient, σzAnd the vertical diffusion coefficient is obtained, y is the horizontal distance from the pollutant diffusion center to the nearest lamp post in the downwind direction, z is the required ground clearance of the lamp post by y, and H is the height of the pollutant diffusion center.
The initial value of the internal parameter b of the Gaussian correction model based on deep learning is historical big data collection, the value is dynamically updated in the training process, calculation and acquisition are carried out according to data of neighbor sensors, and after each round of training is completed, current sensor data of at least 3 intelligent lamp poles closest to each other are acquired for verification.
In order to further solve the problems of single function and inconvenient detection of regional atmospheric pollution detection equipment, the invention also provides an atmospheric pollutant tracing and inspection terminal and system based on the intelligent street lamp, and the specific technical scheme is as follows:
an atmospheric pollutant source tracing investigation terminal based on an intelligent street lamp comprises a data processing module and a communication module, wherein the data processing module executes the atmospheric pollutant source tracing investigation method; the communication module is used for realizing data interaction.
An atmospheric pollutant source tracing and investigation system based on an intelligent street lamp comprises a visualization platform and a plurality of atmospheric pollutant source tracing and investigation terminals, wherein the visualization platform is used as a central server, and the atmospheric pollutant source tracing and investigation terminals are used as sub-servers; and the central server performs data interaction with all the sub-servers, and each sub-server has the functions of independently analyzing atmospheric pollution data and performing ad hoc network with the neighbor sub-servers.
The central server controls the on-off of each sub-server and provides an initial global model for each sub-server; when the training weight value is in work, receiving and processing data sent by each sub-server, and sending the training weight value to each sub-server;
the sub-server collects the atmospheric data with time stamp and space stamp, receives the detection data close to the sub-server, calculates and adjusts the training weight according to the training weight value provided by the central server and the detection data close to the sub-server, retrains and updates the internal parameters of the model, and returns the processed data model to the central server.
The central server receives the pollution source prediction information of the sub-servers, constructs a federal learning neural network model, performs global search on pollution sources in the coverage range of the intelligent lamp poles, determines the position of a final pollution source, and feeds back results to the convolutional neural network model of each intelligent lamp pole.
When the sub-servers send data to the central server, the data are firstly compressed into a data packet form and then sent to the central server for multiple times.
Compared with the prior art, the invention has the following beneficial effects:
1. the method endows various sensing information with time stamps and position stamps, achieves data sharing interaction of a distributed sensing network based on a TCP/IP handshake protocol, constructs a deep learning model by combining multi-mode sensing big data of each lamp pole on the basis of a Gaussian wind point source diffusion model, carries out peripheral concentration estimation and pollution source prediction tracking, trains original deep learning models of the respective lamp poles through the multi-mode sensing big data of the lamp poles of the neighbor nodes, and improves the accuracy of the peripheral concentration estimation and the pollution source prediction tracking.
2. By additionally arranging the related sensors on the intelligent street lamp, a chain for acquiring, processing and deciding information is shortened, the real-time performance of executing control is improved, and meanwhile, the convenience of the intelligent street lamp is utilized, so that the real-time detection is facilitated and the environment data is provided.
3. The sub-servers and the central server perform data interaction in real time, and the central server provides an initial model for the sub-servers and feeds back training weights, so that the sub-servers can detect and predict the atmospheric pollution more accurately.
4. The automatic detection algorithm and the terminal system can be used for environment detection of different places such as chemical industry parks, parks and communities. Can fix a position the pollutant fast, practice thrift manpower and materials, guarantee environmental safety.
Drawings
Fig. 1 is a schematic diagram of module connection of an atmospheric pollutant tracing system based on an intelligent street lamp.
Fig. 2 is a schematic diagram of the geographical location distribution of the atmospheric pollutant traceability system based on the intelligent street lamp.
Wherein, the labels in the figure are: 01-28-ordinary lamp pole; 001-.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The invention relates to an atmospheric pollutant distributed monitoring system based on a smart lamp pole and a source tracing and troubleshooting method. Wisdom lamp pole perception module includes high accuracy positioning sensor, wind speed and wind direction sensor, pollutant monitor. The system is used for collecting atmospheric pollution sensing information coupled with longitude and latitude coordinates; the 5G transmission module comprises a communication base station, a synchronous clock source and an intelligent gateway, wherein the communication base station, the synchronous clock source and the intelligent gateway are arranged on the intelligent lamp pole and are used for transmitting the atmospheric pollution sensing information and the longitude and latitude coordinate information of the unified timestamp; the model calculation module is used for constructing a basic wind field model; fitting a pollutant range model through the monitoring data; calculating a pollutant diffusion center; and the GIS visualization platform is used for visually outputting the three-dimensional position of the pollution source.
An atmospheric pollutant tracing and inspection method based on an intelligent street lamp comprises the following steps:
step 1, acquiring various sensor data around each intelligent lamp pole by applying a sensing module arranged on the intelligent lamp pole, giving a timestamp and a position stamp to the sensor data, and constructing a distributed sensing network based on the intelligent lamp pole;
step 2, constructing an original convolution neural network model for each intelligent lamp pole, and performing deep learning on the convolution neural network models of the respective lamp poles by combining the data of the sensors of the intelligent lamp poles;
step 3, applying a Gaussian correction model based on deep learning to predict sensor data of a neighbor smart lamp pole, and acquiring and outputting prediction information of peripheral atmospheric concentration and pollution sources;
step 4, updating the training weight of the convolutional neural network model according to the data value of the neighbor sensor, training the convolutional neural network model by using the current sensor data of the neighbor sensor, and updating the internal parameters of the Gaussian correction model based on deep learning;
and 5, repeatedly executing the step 3 to the step 4.
An atmospheric pollutant source tracing investigation terminal based on an intelligent street lamp comprises a data processing module and a communication module, wherein the data processing module executes the atmospheric pollutant source tracing investigation method; the communication module is used for realizing data interaction.
An atmospheric pollutant source tracing and investigation system based on an intelligent street lamp comprises a visualization platform and a plurality of atmospheric pollutant source tracing and investigation terminals, wherein the visualization platform is used as a central server, and the atmospheric pollutant source tracing and investigation terminals are used as sub-servers; and the central server performs data interaction with all the sub-servers, and each sub-server has the functions of independently analyzing atmospheric pollution data and performing ad hoc network with the neighbor sub-servers.
Specific embodiment, as shown in figures 1 and 2,
the atmospheric pollutant source tracing and investigation system based on intelligent street lamp comprises a visual platform and a plurality of atmospheric pollutant source tracing and investigation terminals, wherein each atmospheric pollutant source tracing and investigation terminal is installed on a smart lamp pole, and the smart lamp pole is set to be D in sequence1、D2、…、Di、…、DnThe visualization platform is used as a central server, and the atmospheric pollutant tracing and investigation terminal is used as a sub-server; and the central server performs data interaction with all the sub-servers, and each sub-server has the functions of independently analyzing atmospheric pollution data and performing ad hoc network with the neighbor sub-servers.
The atmospheric pollutant source tracing investigation terminal comprises a smart lamp pole sensing module, a 5G transmission module and a model calculation module, wherein the smart lamp pole sensing module comprises but is not limited to a high-precision positioning sensor, a timer, a wind speed and direction sensor, a multi-component pollutant monitor, rainfall, air humidity, various pollutant concentrations and other equipment and is used for collecting atmospheric pollution sensing big data coupling space-time parameters and a near-earth atmospheric dynamics state; the model calculation module comprises a Gaussian correction model based on deep learning and a convolutional neural network model, has edge AI computing capacity, processes data acquired by the intelligent lamp pole sensing module according to the process of the atmospheric pollutant tracing and investigation method, and outputs the processing result to the visualization platform through the 5G transmission module.
The 5G transmission module comprises a communication base station, a synchronous clock source and an intelligent gateway which are arranged on the intelligent lamp pole and used for transmitting information such as near-ground atmospheric pollutant data, high-dimensional semantic extraction features, pollution source reasoning results and the like of coupling space-time dynamics information under the uniform timestamp, the intelligent lamp poles in different areas are used as perception nodes to achieve interconnection and intercommunication, and a data sharing driven distributed intelligent perception network is constructed.
The visual platform is a GIS visual platform, is connected to a smart lamp pole distributed sensing network, and visually outputs the position of a pollution source and the long time sequence dynamic diffusion process of different atmospheric pollutants by using a digital twinning method. And pollutant diffusion deduction and tracing are realized by a method of combining distributed space-time data federal learning with a near-earth atmospheric pollution diffusion model.
The tracing and checking method of the atmospheric pollutant tracing and checking system specifically comprises the following steps:
first step, application installation are at wisdom lamp pole D1、D2、…、Di、…、DnThe sensing module acquires various sensor data around each intelligent lamp pole, gives a time stamp and a position stamp, and constructs a distributed sensing network based on the intelligent lamp pole and the GIS visual platform; and data sharing interaction of the distributed sensing network is realized based on a TCP/IP handshake protocol.
Secondly, the GIS visual platform sends an initial convolutional neural network model and a Gaussian correction model based on deep learning to a terminal of each intelligent lamp pole, the terminal on each intelligent lamp pole constructs an original convolutional neural network model, and the convolutional neural network models of the respective lamp poles are deeply learned by combining sensor data of the terminal;
thirdly, predicting sensor data of a neighbor smart lamp post by using a Gaussian correction model based on deep learning, and acquiring and outputting prediction information of peripheral atmospheric concentration and pollution sources;
during prediction, wind speed, humidity and rainfall in the current environment all affect a Gaussian correction model based on deep learning, and the wind speed, the humidity and the rainfall are states of nonlinear change. The specific representation of the Gaussian correction model based on deep learning is as follows:
Ri＝(b,Vi,Cij) Wherein R isiFor intelligent lamp post DiRelative distance from the center of diffusion of the contaminant, b ═ Vi,HiAnd f) is the internal parameter of the Gaussian correction model based on deep learning, ViFor intelligent lamp post DiDetected wind speed, HiFor intelligent lamp post DiDetected humidity, f is whether rainfall is present, CijFor intelligent lamp post DiAnd (4) detecting the concentration of the jth pollutant, wherein i and j are positive integers. The initial value source of the internal parameter b of the Gaussian correction model based on deep learning is historical big data collection, the initial value is a dynamically updated value in the training process, the initial value is calculated and obtained according to the data of the neighbor sensor, and after each round of training is finished, the current sensor data of at least 3 intelligent lamp poles closest to each other are obtained for verification;
meanwhile, the pollutant discharge amount Q in unit time is calculated according to the following formula:
Q＝2πCij*V*σy*σz/{e^(-y2/2σy 2)*{e^[-(z-H)2/2σy 2]+e^[-(z+H)2/2σz 2]}}
wherein V is the average wind speed at the discharge outlet, σyIs the lateral diffusion coefficient, σzAnd the vertical diffusion coefficient is obtained, y is the horizontal distance from the pollutant diffusion center to the nearest lamp post in the downwind direction, z is the required height of the lamp post from the ground, and H is the height of the pollutant diffusion center.
Fourthly, updating the training weight of the convolutional neural network model according to the data value of the neighbor sensor, training the convolutional neural network model by using the current sensor data, and updating the internal parameters of the Gaussian correction model based on deep learning; the terminal of every wisdom lamp pole collects the atmospheric data that self has time stamp and space stamp, receives the detection data that closes on wisdom lamp pole terminal, and according to the training weight value that central server provided and the detection data that closes on wisdom lamp pole terminal, calculation and adjustment training weight retrain and update the model intrinsic parameter, return the data model who will handle back to central server. When sending data to the central server, because the data volume is large, in order to avoid data loss during sending and receiving, the data should be compressed into a data packet form, and then sent to the central server for multiple times.
Furthermore, the step can also include a process of judging prediction data, namely receiving detection data transmitted by other lamp poles, comparing the detection data with trained data, and when an error value between the detection data and the trained data is within a preset threshold range, sending a predicted value to the central server, otherwise, not sending the predicted value, and continuing to adjust the weight until the trained model internal parameters meet the condition that the predicted value accords with the detection data of the surrounding lamp poles.
And fifthly, the central server receives the pollution source prediction information of the sub-servers, a federal learning neural network model is constructed, the pollution source in the coverage range of the intelligent lamp pole is globally searched, the final pollution source position is determined, and results are fed back to the convolutional neural network model of each intelligent lamp pole.
As shown in fig. 2, in an area, a plurality of ordinary lamp poles are provided, a terminal of the scheme is installed on a lamp pole number 001-004 to serve as a smart lamp pole, when the terminal number 001 performs data processing, the data of a sensor and the data of a sensor at a terminal number 002-, and training according to the new weight, updating the internal parameters of the Gaussian correction model based on deep learning, and repeating the process until the error range is reached. The working process of other terminals is the same.
The data listed in table 1 below are predicted values and errors from the true values for four smart light poles according to the described method, all in meters, with respect to a plurality of different distance pollution sources, wherein,
the first column is that the numbers of the lamp posts respectively correspond to 001-; the second row is the distance between a plurality of preset pollution sources and four intelligent lamp poles; the third column is the position of the pollution source away from the lamp pole, which is estimated through a Gaussian correction model based on deep learning after the convolution neural network is updated; the fourth column is the relative error of the predicted value and the preset value.
Only a few sets of data are listed in table 1 for purposes of illustration and verification of the results obtained by the method. As can be seen from the error values in table 1, the largest value also appears second after the decimal point, and therefore, the accuracy of prediction using this method is very high. The prediction accuracy of the system is higher and higher with the increasing data volume and the increasing running time.
TABLE 1
| Lamp post number | True relative distance | Prediction value | Error of the measurement |
| 1 | 20 | 19.48095 | 0.026644 |
| 2 | 50 | 48.72426 | 0.026183 |
| 3 | 40 | 39.38646 | 0.015577 |
| 4 | 70 | 69.31296 | 0.009912 |
| 1 | 40 | 39.27716 | 0.018404 |
| 2 | 20 | 19.67016 | 0.016768 |
| 3 | 10 | 9.534927 | 0.048776 |
| 4 | 50 | 49.97158 | 0.000569 |
| 1 | 60 | 59.87853 | 0.002029 |
| 2 | 20 | 19.12972 | 0.045494 |
| 3 | 10 | 9.325307 | 0.072351 |
| 4 | 30 | 29.94676 | 0.001778 |
| 1 | 60 | 59.40178 | 0.010071 |
| 2 | 30 | 28.68822 | 0.045725 |
| 3 | 10 | 9.662353 | 0.034945 |
| 4 | 20 | 19.15549 | 0.044087 |
| 1 | 50 | 49.30998 | 0.013994 |
| 2 | 40 | 39.7244 | 0.006938 |
| 3 | 80 | 78.83078 | 0.014832 |
| 4 | 20 | 19.59321 | 0.020762 |
| 1 | 40 | 39.4894 | 0.01293 |
| 2 | 30 | 28.70473 | 0.045124 |
| 3 | 40 | 39.07558 | 0.023657 |
| 4 | 70 | 68.66055 | 0.019508 |
In order to improve the accuracy of peripheral concentration estimation and pollution source prediction tracking, the number of intelligent lamp poles can be increased, and the terminal of the scheme can be installed on a corresponding common lamp pole.
The central server controls the on-off of each sub-server, evaluates the performance of each sub-server, provides training weight for each sub-server, processes data packets provided by each sub-server, and needs to read data to judge whether the sub-servers exceed the threshold value due to the fact that the detection distance has the threshold value, and selects the sub-servers for subsequent processing.
After the training of each intelligent lamp pole terminal is finished, the training model and the training data are uploaded to the central server, and due to the fact that the problem of building shielding and diffusion threshold exists, the central server finally reconfirms a final pollutant diffusion center according to the prediction accuracy and the final prediction result of each intelligent lamp pole and uploads the final pollutant diffusion center to the visual interface.
In order to further improve the prediction precision, after the information such as the pollution source, the type concentration and the like is determined, the pollution source can be further detected and checked more finely by the unmanned aerial vehicle or unmanned vehicle carrying pollution detection equipment, and the prediction accuracy is determined.
It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In this application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings. These terms are used primarily to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.
Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meaning of these terms in this application will be understood by those of ordinary skill in the art as appropriate.
The above description is of the preferred embodiment of the invention. It is to be understood that the invention is not limited to the particular embodiments described above, in that devices and structures not described in detail are understood to be implemented in a manner common in the art; those skilled in the art can make many possible variations and modifications to the disclosed solution, or modify the equivalent embodiments with equivalent variations, without departing from the scope of the solution, without thereby affecting the spirit of the invention. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the protection scope of the technical solution of the present invention, unless the content of the technical solution of the present invention is departed from.
Claims (10)
1. An atmospheric pollutant source tracing investigation method based on an intelligent street lamp is characterized in that: the method comprises the following steps:
step 1, acquiring various sensor data around each intelligent lamp pole by applying a sensing module arranged on the intelligent lamp pole, giving a timestamp and a position stamp to the sensor data, and constructing a distributed sensing network based on the intelligent lamp pole;
step 2, constructing an original convolutional neural network model for each intelligent lamp pole, and performing deep learning on the convolutional neural network model of each lamp pole by combining the data of the sensor of each intelligent lamp pole;
step 3, applying a Gaussian correction model based on deep learning to predict sensor data of a neighbor smart lamp pole, and acquiring and outputting prediction information of peripheral atmospheric concentration and pollution sources;
step 4, updating the training weight of the convolutional neural network model according to the data value of the neighbor sensor, training the convolutional neural network model by using the current sensor data of the neighbor sensor, and updating the internal parameters of the Gaussian correction model based on deep learning;
and 5, repeatedly executing the step 3 to the step 4.
2. The atmospheric pollutant source tracing and inspection method based on the intelligent street lamp as claimed in claim 1, wherein: the sensor data includes, but is not limited to, location, time, wind speed, wind direction, precipitation, air humidity, various pollutant concentrations.
3. The atmospheric pollutant source tracing and inspection method based on the intelligent street lamp as claimed in claim 2, wherein: the deep learning-based Gaussian correction model is specifically represented as follows:
Ri＝(b,Vi,Cij) Wherein R isiFor intelligent lamp post DiRelative distance from the center of diffusion of the contaminant, b ═ Vi,HiAnd f) is the internal parameter of the Gaussian correction model based on deep learning, ViFor intelligent lamp post DiDetected wind speed, HiFor intelligent lamp post DiDetected humidity, f is whether rainfall is present, CijFor intelligent lamp post DiAnd (4) detecting the concentration of the j pollutant, wherein i and j are positive integers.
4. The atmospheric pollutant source tracing and inspection method based on the intelligent street lamp as claimed in claim 3, wherein: the pollutant discharge amount Q per unit time is calculated according to the following formula:
Q＝2πCij*V*σy*σz/{e^(-y2/2σy 2)*{e^[-(z-H)2/2σy 2]+e^[-(z+H)2/2σz 2]}}
wherein V is the average wind speed at the discharge outlet, σyIs the lateral diffusion coefficient, σzAnd the vertical diffusion coefficient is obtained, y is the horizontal distance from the pollutant diffusion center to the nearest lamp post in the downwind direction, z is the required ground clearance of the lamp post by y, and H is the height of the pollutant diffusion center.
5. The atmospheric pollutant source tracing and inspection method based on the intelligent street lamp as claimed in claim 3, wherein: the initial value of the internal parameter b of the Gaussian correction model based on deep learning is historical big data collection, the value is dynamically updated in the training process, calculation and acquisition are carried out according to the data of the neighbor sensor, and after each round of training is finished, the current sensor data of at least 3 intelligent lamp poles closest to each other are acquired for verification.
6. The utility model provides an atmospheric pollutants investigation terminal of tracing to source based on intelligence street lamp which characterized in that: the atmospheric pollutant source tracing and inspection method comprises a data processing module and a communication module, wherein the data processing module executes the atmospheric pollutant source tracing and inspection method according to any one of claims 1 to 5; the communication module is used for realizing data interaction.
7. The utility model provides an atmospheric pollutants investigation system of tracing to source based on intelligence street lamp which characterized in that: the atmospheric pollutant source tracing and inspection terminal comprises a visualization platform and a plurality of atmospheric pollutant source tracing and inspection terminals as claimed in claim 6, wherein the visualization platform is used as a central server, and the atmospheric pollutant source tracing and inspection terminals are used as sub-servers; and the central server performs data interaction with all the sub-servers, and each sub-server has the functions of independently analyzing atmospheric pollution data and performing ad hoc network with the neighbor sub-servers.
8. The atmospheric pollutant source-tracing troubleshooting system based on intelligent street lamp of claim 7, characterized in that: the central server controls the on-off of each sub-server and provides an initial global model for each sub-server; when the training weight value is in work, receiving and processing data sent by each sub-server, and sending the training weight value to each sub-server;
the sub-server collects the atmospheric data with time stamp and space stamp, receives the detection data close to the sub-server, calculates and adjusts the training weight according to the training weight value provided by the central server and the detection data close to the sub-server, retrains and updates the internal parameters of the model, and returns the processed data model to the central server.
9. The atmospheric pollutant source-tracing troubleshooting system based on intelligent street lamp of claim 7, characterized in that: the central server receives the pollution source prediction information of the sub-servers, constructs a federal learning neural network model, performs global search on pollution sources in the coverage range of the intelligent lamp poles, determines the position of a final pollution source, and feeds back results to the convolutional neural network model of each intelligent lamp pole.
10. The atmospheric pollutant source-tracing troubleshooting system based on intelligent street lamp of claim 7, characterized in that: when the sub-servers send data to the central server, the data are firstly compressed into a data packet form and then sent to the central server for multiple times.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210208991.7A CN114581278A (en) | 2022-03-03 | 2022-03-03 | Atmospheric pollutant tracing and troubleshooting method, terminal and system based on intelligent street lamp |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210208991.7A CN114581278A (en) | 2022-03-03 | 2022-03-03 | Atmospheric pollutant tracing and troubleshooting method, terminal and system based on intelligent street lamp |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114581278A true CN114581278A (en) | 2022-06-03 |
Family
ID=81774234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210208991.7A Pending CN114581278A (en) | 2022-03-03 | 2022-03-03 | Atmospheric pollutant tracing and troubleshooting method, terminal and system based on intelligent street lamp |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114581278A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116011317A (en) * | 2022-11-29 | 2023-04-25 | 北京工业大学 | Small-scale near-real-time atmospheric pollution tracing method based on multi-method fusion |
| RU2818685C1 (en) * | 2023-06-19 | 2024-05-03 | федеральное государственное автономное образовательное учреждение высшего образования "Национальный исследовательский университет "Высшая школа экономики" | Method of identifying a source of emission of harmful substances into the atmosphere based on artificial intelligence technology |
-
2022
- 2022-03-03 CN CN202210208991.7A patent/CN114581278A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116011317A (en) * | 2022-11-29 | 2023-04-25 | 北京工业大学 | Small-scale near-real-time atmospheric pollution tracing method based on multi-method fusion |
| CN116011317B (en) * | 2022-11-29 | 2023-12-08 | 北京工业大学 | Small-scale near-real-time atmospheric pollution tracing method based on multi-method fusion |
| RU2818685C1 (en) * | 2023-06-19 | 2024-05-03 | федеральное государственное автономное образовательное учреждение высшего образования "Национальный исследовательский университет "Высшая школа экономики" | Method of identifying a source of emission of harmful substances into the atmosphere based on artificial intelligence technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110531030B (en) | Method and device for analyzing atmospheric pollutants based on Internet of things big data | |
| CN114371260B (en) | Method for performing gridding monitoring, diffusion early warning and tracing on industrial enterprise unstructured VOCs | |
| CN110081930B (en) | Land, sea and air integrated ecological environment monitoring system | |
| CN106651100B (en) | Air quality evaluation system and method based on vehicle-mounted monitoring points optimized through Internet of vehicles | |
| CN111458721B (en) | Exposed garbage identification and positioning method, device and system | |
| CN106950334A (en) | A kind of moving monitoring system of spatially distributed urban air environmental quality | |
| CN114757807B (en) | Multi-mode fused online accounting method for actual emission of atmospheric pollutants | |
| CN116539829A (en) | Water quality monitoring sensing analysis method | |
| CN113436045A (en) | Atmospheric pollution multi-scale fusion traceability method and device and readable storage medium | |
| CN114088885B (en) | Atmospheric pollutant walks detection system that navigates | |
| CN108802856B (en) | AI-based source data dynamic correction and forecast system and working method thereof | |
| CN115759488A (en) | Carbon emission monitoring and early warning analysis system and method based on edge calculation | |
| CN115185292B (en) | Air pollution intelligent monitoring method and platform based on ground and air integration | |
| CN113655175A (en) | Gridding air monitoring method, system, computer equipment and storage medium | |
| CN110910440A (en) | Power transmission line length determination method and system based on power image data | |
| CN114581278A (en) | Atmospheric pollutant tracing and troubleshooting method, terminal and system based on intelligent street lamp | |
| CN114518143A (en) | Intelligent environment sensing system | |
| CN112446543A (en) | Urban underground comprehensive pipe gallery risk management and control system and method based on neural network | |
| CN113267601A (en) | Industrial production environment remote real-time monitoring cloud platform based on machine vision and data analysis | |
| CN116258101B (en) | Method for rapidly calculating emission source intensity based on gas concentration monitoring data | |
| CN112926863A (en) | Power grid disaster comprehensive monitoring system based on six early warning centers | |
| CN112561857A (en) | Unmanned aerial vehicle-based photovoltaic panel dust detection system and detection method | |
| CN116630787A (en) | Light-weight detection method and device for overflow of garbage can and storage device | |
| CN115471128A (en) | Big data-based device for predicting air quality trend | |
| CN116147712A (en) | Space-time restriction-free three-dimensional construction environment monitoring device and prediction 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 |