CN106067079A - A kind of system and method for gray haze based on BP neutral net prediction - Google Patents
A kind of system and method for gray haze based on BP neutral net prediction Download PDFInfo
- Publication number
- CN106067079A CN106067079A CN201610446390.4A CN201610446390A CN106067079A CN 106067079 A CN106067079 A CN 106067079A CN 201610446390 A CN201610446390 A CN 201610446390A CN 106067079 A CN106067079 A CN 106067079A
- Authority
- CN
- China
- Prior art keywords
- data
- gray haze
- prediction
- module
- haze
- 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.)
- Granted
Links
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"
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
The invention provides the system and method for a kind of gray haze based on BP neutral net prediction, this system includes: excavate the relation between the air quality data collected by BP neutral net, prediction air quality and haze weather development trend, provide early warning to haze weather；It is characterized in that: include data acquisition module, data base, data compilation module, gray haze predictive server, data preprocessing module, learning of neuron module, BP neural network prediction module, WEB server and mobile terminal；Its method is: gray haze prognoses system is described as the self study prognoses system of multiple-input and multiple-output, input the gray haze and air quality data gathered, by self study and the adaptive ability of neutral net, it was predicted that the development trend that haze weather is possible, and reduce forecast error；The present invention can utilize existing gray haze observation data to make a prediction gray haze development, it is possible to gos deep into excavation and has inputted the complex relationship between data, obtains relatively accurately prediction effect.
Description
Technical field
The present invention relates to a kind of gray haze Forecasting Methodology and technology, the prediction of a kind of gray haze based on BP neutral net
System and method.
Background technology
At present, the gray haze phenomenon of China is more and more concerned, about forecast analysis and the research layer of Management strategy of gray haze
Go out not poor, and the gray haze forecast analysis technology set up at present mainly includes gray haze monitoring, gray haze assessment, strategy prediction, strategy
The aspects such as enforcement.Current gray haze Forecasting Methodology and system, mainly monitoring with ecological environment and air quality indexes is that master enters
Row modeling, utilize the indexs such as the PM2.5, PM1.0 that monitor to attempt accurately to describe gray haze mathematical model and mechanism of Evolution, up-to-date
Technology be additionally included in the technology such as gray haze hotspots placement sensor network and satellite image analysis, for gray haze monitoring and
Early warning provides data a large amount of, accurate, then, analyzes and predicts the development trend of gray haze on this basis, thus formulate phase
Close gray haze prophylactico-therapeutic measures.
Current gray haze prediction analysis method and system shortcoming are it is also obvious that need to set up mathematics letter to different data
Number, including PM2.5, PM1.0 material thing, carbon dioxide, nitrogen dioxide, sulfur monoxide etc., the entity of these different attributes is at meter
It is differentiated for counting in.It addition, the development of gray haze and prediction also have substantial connection, root with local geographical environment and productive life
Predict that gray haze must take into the disturbed condition between different pieces of information according to these data.And, the natural environment residing for gray haze and
Social environment has self study character, and traditional Forecasting Methodology is difficult to consider this point.At home, exist along with data processing technique
Application in gray haze prediction, for utilizing data acquisition and self-learning method prediction gray haze to provide condition, but, in the market
Seldom there are gray haze Forecasting Methodology based on BP neutral net and system.
Summary of the invention
In order to overcome the defect of above-mentioned prior art, the invention provides the prediction of a kind of gray haze based on BP neutral net
System and method, excavates the relation between the various data that gray haze is relevant and self-study mechanism by BP neutral net, for ash
The prediction of haze and decision-making provide data support.
The technical solution adopted in the present invention is:
The system of a kind of gray haze based on BP neutral net prediction, including data acquisition module, gray haze data base, gray haze prediction clothes
Business device, WEB server, mobile terminal.Data acquisition module connects gray haze data base, and gray haze data base connects gray haze prediction service
Device, gray haze predictive server connects WEB server, mobile terminal respectively.
Described several data acquisition module: data acquisition module will be obtained and gray haze phase by various sensors and monitoring equipment
The data of collection are stored in gray haze data base by the data closed.
Described several data acquisition module: the data message of collection must be to be gathered by the department such as National Environmental, statistics is unified
And typing, it is ensured that information source accuracy.
Gray haze data base: for depositing the data such as pellet, sulfur dioxide and the nitrogen oxides relevant to gray haze；
Gray haze data base: issued by China Meteorological department or gray haze authoritative institution, managed and update, the data collected are stored in
Data base, is transferred to gray haze predictive server after necessary data compilation.
Gray haze data base includes stating data compilation module, and described data compilation module is by the data of data collecting module collected
Carrying out arranging, collecting, these data are probably derived from different data bases or data set, and data are the most incomplete, scarce
Lose, containing noisy, this low-quality data input cannot obtain high-quality predicting the outcome, need to carry out data whole
Reason, in order to concentrate in gray haze data base and focus on；
Described data compilation module: to different data, use different data processing methods, in order to data compilation is become unified
Form, and it is stored in gray haze data base.
Gray haze predictive server: take out the data in gray haze data base, carries out data prediction and inputoutput data
Initialize, the training parameter of BP neutral net, learning of neuron and fitting function curve be set, it was predicted that value and actual comparison,
Constantly revise the amount of being currently entered, until training error is less than setting value, finally export premeasuring；
Gray haze predictive server: including stable learning of neuron method, error is little, rapid and convenient, and will finally predict
Result networking shows and is sent to mobile terminal.
Described gray haze predictive server includes data preprocessing module, neuron training module, BP neural network prediction mould
Block.
Described data preprocessing module: the data will taken out from gray haze data base, is normalized, makes data divide
It is distributed between [-1 ~+1], prepares high-quality data for learning of neuron training；
Gray haze predictive server includes, simple scalability, sample-by-sample average abatement and the method such as feature normalization, is made by pretreatment
BP algorithm can play optimum prediction effect.
Described neuron training module, after setting training parameter, neuron passes through self study, utilizes reality output and phase
Hope that network weight coefficient is modified by the error between output, finally output optimum prediction effect；
Described neuron training module also includes: neuron self study, self-adaptative adjustment Learning Step, and the forward completing information passes
Broadcast the back propagation with error
Described neuron training module includes that BP algorithm, BP algorithm have a preferable convergence property, preferable self study and adaptive
Should be able to power, fault-tolerant ability.
Described BP neural network prediction module, predicts the outcome to neuron and exports, simultaneously by data renormalization,
Data under index identical with initial data.
Described BP neural network prediction module, will predict the outcome input WEB server and mobile terminal, the most efficiently ash
Haze early warning.
Described WEB server: can predict gray haze development trend, will predict the outcome and be converted to the form such as chart, broken line graph,
It is sent to relevant weather department；
Described WEB server: correspond to the gray haze of each grade by predicting the outcome, according to gray haze exponential case, makes corresponding
Early warning, formulate corresponding gray haze Management strategy.
Described mobile terminal: predict the outcome and be converted to air quality index or chart, predict the outcome broken line graph, is sent to
In mobile phone users hands, go on a journey for user and suggestion is provided.
Described mobile terminal: user can be with real-time query gray haze index of correlation situation, and mobile terminal gives the use that will go out
Family provides corresponding suggestion, conveniently reminds user.
The system and method for a kind of gray haze based on BP neutral net of present invention prediction, has the advantage that:
1: first, gray haze prognoses system is modeled as the system of a kind of multiple-input and multiple-output by the present invention, it is possible to PM2.5, PM1.0
Material thing, carbon dioxide, nitrogen dioxide, sulfur monoxide etc., the entity of these different attributes calculates.
2: secondly, it is possible to calculate according to local geography and productive life data, and consider doing between different pieces of information
Disturb situation, in conjunction with providing prediction after practical situation, improve the accuracy of gray haze prediction.
3: again, the present invention has self-learning property, it is possible to consider the self-learning property of the systems such as production, life, environment,
Thus adjust neuron and the parameter of neutral net and training according to the input of external data, propose to optimize and solution.
4: the present invention is described as the self study prognoses system of multiple-input and multiple-output gray haze prognoses system, input has gathered
Gray haze and air quality data, by self study and the adaptive ability of neutral net, it was predicted that the Developing Tendency that haze weather is possible
Gesture, and reduce forecast error；The present invention can utilize existing gray haze observation data to make a prediction gray haze development, it is possible to deeply
Excavate and inputted the complex relationship between data, obtain more accurate resolution.
Accompanying drawing explanation
Fig. 1 is present configuration schematic diagram.
Fig. 2 is inventive algorithm flow chart.
Fig. 3 is that the present invention predicts the outcome figure.
Detailed description of the invention
As it is shown in figure 1, the system of a kind of gray haze based on BP neutral net prediction, including such as lower module: data acquisition module
Block 100, data base 101, data compilation module 102, gray haze predictive server 103, data preprocessing module 104, neuron
Practise module 105, BP neural network prediction module 106, WEB server 107 and mobile terminal 108.
Gray haze Forecasting Methodology is described as the neural network forecasting system of a kind of multiple-input and multiple-output by described system, by god
Self-study mechanism through unit, it was predicted that possible gray haze development trend；Inputoutput data is excavated by BP neural network model
Between the internal relations that exists, the incidence relation between continuous matching input data, reduced by constantly feedback and study mechanism
Forecast error, provides reference for gray haze preventing and treating.
Described data acquisition module 100 includes various sensor and monitoring equipment, is installed on various places environmental system, obtain with
The data of collection are stored in gray haze data base by the data that gray haze is relevant；According to described data acquisition module 100, the number of collection
It is believed that breath must be to be gathered and typing by the department such as National Environmental, statistics is unified, it is ensured that information source accuracy.
Described gray haze data base 101 includes high-performance data storehouse and memory module, is installed in environmental monitoring division data
The heart, for depositing the data such as pellet, sulfur dioxide and the nitrogen oxides relevant to gray haze；Described gray haze data base
101, issued by China Meteorological department or gray haze authoritative institution, managed and update, the data collected are stored in data base, pass through
It is transferred to gray haze predictive server 103 after necessary data compilation.
Described data compilation module 102 is installed on server, including backstage algorithm and interface display, by data acquisition module
The data that block 100 gathers carry out arranging, collecting, and these data are probably derived from different data bases or data set, and data are led to
Be often incomplete, disappearance, containing noisy, this low-quality data input cannot obtain high-quality predicting the outcome,
Need to carry out data compilation, in order to concentrate in gray haze data base 100 and focus on；Described data compilation module 102 includes,
To different data acquisitions by different data processing methods, in order to data correct principle is become consolidation form, and is stored in gray haze data base
101。
Described gray haze predictive server 103 is high-performance server, is installed on environmental monitoring department, takes out gray haze data base
Data in 101, carry out the initialization of data prediction and inputoutput data, arrange the training parameter of BP neutral net, god
Through meta learning and fitting function curve, it was predicted that value and actual comparison, constantly revise the amount of being currently entered, until training error is less than
Till setting value, finally export premeasuring.Described gray haze predictive server 103, it is possible to the gray haze prediction of response user and inquiry
Request, possesses stable learning of neuron method, and the networking that finally predicts the outcome is shown and be sent to mobile terminal.
Described data preprocessing module 104 is installed on server, for the number that will take out from gray haze data base 101
According to, it is normalized, makes data be distributed between [-1 ~+1], prepare high-quality data for learning of neuron training.
Described neuron training module 105 is installed on server, and after setting training parameter, neuron is by learning by oneself
Practise, utilize the error between reality output and desired output that network weight coefficient is modified, finally output optimum prediction effect
Really.
Neuron is predicted the outcome and exports by described BP neural network prediction module 1, simultaneously by data renormalization,
Data under index identical with initial data.Described BP neural network prediction module 106, will predict the outcome input WEB clothes
Business device 107 and mobile terminal 108, gray haze early warning the most efficiently.
Described WEB server 107 is installed on various places environmental monitoring department and user, can predict gray haze development trend, will
Predict the outcome and be converted to the form such as chart, broken line graph, be sent to relevant weather department.Described WEB server 107, will prediction
Result corresponds to the gray haze of each grade, according to gray haze exponential case, makes corresponding early warning, formulates corresponding gray haze and administers plan
Slightly.
Described mobile terminal 108: predict the outcome and be converted to air quality index or chart, predict the outcome broken line graph, sends out
Delivering in mobile phone users hands, going on a journey for user provides suggestion.User can be mobile with real-time query gray haze index of correlation situation
Terminal provides corresponding suggestion to the user that will go out, and conveniently reminds user.
As in figure 2 it is shown, a kind of based on BP neutral net the gray haze Forecasting Methodology algorithm flow provided for present example
Figure, it is characterised in that include such as lower module, collects gray haze data and normalized, given input and output vector, calculates defeated
Going out result, it is desirable to value output result, it is desirable to value output and actual deviation, whether error meets calculates termination condition, it was predicted that gray haze
Index.According to described neuron training and workflow, the method includes, neuron self study, self-adaptative adjustment study step
Long, complete the forward-propagating of information and the back propagation of error.According to described algorithm flow, it is characterised in that the method bag
Including, BP algorithm has preferable convergence property, preferable self study and adaptive ability, fault-tolerant ability.
As it is shown on figure 3, a kind of based on BP neutral net the gray haze Forecasting Methodology for present example offer predicts the outcome
Figure, it is possible to meet real data.According to described prediction algorithm flow process, the method includes, simple scalability, sample-by-sample average are cut down
With methods such as feature normalization, BP algorithm is enable to play optimum prediction effect by pretreatment.
In Fig. 3, it can be seen that the dispersion of air quality data (data point as in Fig. 3) is bigger, and it is carried out standard
Really predict it is the difficult point of environmental forecasting and Air Quality Forecast all the time.Described method can be to PM2.5, PM1.0 material
Thing, carbon dioxide, nitrogen dioxide, sulfur monoxide etc., the entity of these different attributes calculates, and carries out the most pre-
Survey (such as Fit curve in Fig. 3).Further, described method can calculate the data of the systems such as production, life, environment and carry out
Self study, thus obtain resolution targetedly.
Embodiment of above is only applicable to illustrate the present invention, and not limitation of the present invention, general about technical field
Logical technical staff, in the case of without departing from the precision of the present invention and scope, it is also possible to make a variety of changes and modification, therefore institute
The technical scheme having equivalent falls within scope of the invention, and the patent protection category of the present invention should limit from claim.
Claims (7)
1. a system for gray haze based on BP neutral net prediction, including data acquisition module (100), gray haze data base
(101), gray haze predictive server (103), WEB server (107), mobile terminal (108)；Data acquisition module (100) connects
Gray haze data base (101), gray haze data base (101) connects gray haze predictive server (103), gray haze predictive server (103) point
Do not connect WEB server (107), mobile terminal (108)；It is characterized in that: described data acquisition module (100), by various
Sensor obtains the data relevant to gray haze with monitoring equipment, and the data of collection are stored in gray haze data base (101)；
Described gray haze data base (101), for depositing pellet, sulfur dioxide and the nitrogen oxides number relevant to gray haze
According to；
Described gray haze predictive server (103), is used for taking out the data in gray haze data base (101), carry out data prediction and
The initialization of inputoutput data, arranges the training parameter of BP neutral net, learning of neuron and fitting function curve, it was predicted that value
And actual comparison, constantly revise the amount of being currently entered, until training error is less than setting value, finally export premeasuring；Institute
State WEB server (107), for corresponding to the gray haze of each grade by predicting the outcome, according to gray haze exponential case, make corresponding
Early warning, formulate corresponding gray haze Management strategy；Described mobile terminal (108), is converted to air quality for predicting the outcome
Index or chart, predict the outcome broken line graph, is sent in mobile phone users hands, goes on a journey offer suggestion for user.
A kind of system of gray haze based on BP neutral net prediction, it is characterised in that: described data
Acquisition module (100), the data message of collection is by National Environmental, the unified collection of statistical department and typing；Data acquisition module
(100) issued by China Meteorological department or gray haze authoritative institution, managed and update, the data collected are stored in gray haze data base
(101) after data compilation, it is transferred to gray haze predictive server (103).
A kind of system of gray haze based on BP neutral net prediction, it is characterised in that: described gray haze
Data base (101) includes stating data compilation module (102), and data acquisition module (100) is gathered by data compilation module (102)
Data carry out arranging, collecting, and these data are probably derived from different data bases or data set, and data are the most imperfect
, disappearance, containing noisy, the input of this low-quality data cannot obtain high-quality predicting the outcome, and needs to count
According to arrangement, in order to concentrate in gray haze data base (101) and focus on.
A kind of system of gray haze based on BP neutral net prediction, it is characterised in that: described data
Sorting module (102), for different data, uses different data processing methods, in order to data correct principle becomes unified lattice
Formula, and it is stored in gray haze data base (101).
A kind of system of gray haze based on BP neutral net prediction, it is characterised in that: described gray haze
Predictive server (103) includes data preprocessing module (104), neuron training module (105), BP neural network prediction module
(106)；
Data preprocessing module (104) includes simple scalability, sample-by-sample average abatement and feature normalization method, pre-by data
Processing module (104), enables BP algorithm to play optimum prediction effect；
After neuron training module (105) sets training parameter, neuron passes through self study, utilizes reality output defeated with expectation
Network weight coefficient is modified by the error between going out, finally output optimum prediction effect；
BP neural network prediction module (106), exports for predicting the outcome neuron, simultaneously by data renormalization,
Obtain the data under index identical with initial data；BP neural network prediction module (106) will predict the outcome input WEB server
(107), mobile terminal (108).
A kind of system of gray haze based on BP neutral net prediction, it is characterised in that: described WEB
Server (107), is used for predicting gray haze development trend, will predict the outcome and be converted to chart, broken line graph form, forms form, sends out
Give relevant weather department.
7. the method for gray haze based on a BP neutral net prediction, it is characterised in that: gray haze Forecasting Methodology is described as one
The neural network forecasting system of multiple-input and multiple-output, by the self-study mechanism of neuron, it was predicted that possible gray haze development trend；
The internal relations existed between inputoutput data is excavated, between continuous matching input data by BP neural network model
Incidence relation, reduces forecast error by constantly feedback and study mechanism, provides reference for gray haze preventing and treating.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610446390.4A CN106067079B (en) | 2016-06-20 | 2016-06-20 | System and method for predicting dust haze based on BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610446390.4A CN106067079B (en) | 2016-06-20 | 2016-06-20 | System and method for predicting dust haze based on BP neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106067079A true CN106067079A (en) | 2016-11-02 |
| CN106067079B CN106067079B (en) | 2021-01-26 |
Family
ID=57420447
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610446390.4A Active CN106067079B (en) | 2016-06-20 | 2016-06-20 | System and method for predicting dust haze based on BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106067079B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108183928A (en) * | 2017-11-27 | 2018-06-19 | 易瓦特科技股份公司 | It is warned based on remote server the method, apparatus and system in gray haze source |
| CN108427905A (en) * | 2017-11-27 | 2018-08-21 | 易瓦特科技股份公司 | The method, apparatus and system warned to gray haze source based on remote server |
| CN108872040A (en) * | 2018-09-30 | 2018-11-23 | 徐州工业职业技术学院 | A kind of city haze monitoring system |
| CN109242166A (en) * | 2018-08-25 | 2019-01-18 | 中科绿建（天津）科技发展有限公司 | A kind of environmental forecasting prevention and control system based on multiple dimensioned deep neural network |
| CN109363668A (en) * | 2018-09-03 | 2019-02-22 | 北京邮电大学 | Cerebral disease forecasting system |
| CN109492759A (en) * | 2018-12-17 | 2019-03-19 | 北京百度网讯科技有限公司 | Neural Network model predictive method, apparatus and terminal |
| CN110011994A (en) * | 2019-03-26 | 2019-07-12 | 惠州学院 | A kind of EMS based on big data |
| CN110654202A (en) * | 2018-06-28 | 2020-01-07 | 大众汽车有限公司 | Ventilation of the interior of a vehicle |
| CN113067870A (en) * | 2021-03-18 | 2021-07-02 | 山东渤聚通云计算有限公司 | Device data processing method and device and server device |
| CN113219871A (en) * | 2021-05-07 | 2021-08-06 | 淮阴工学院 | Curing room environmental parameter detecting system |
| CN113970511A (en) * | 2021-10-21 | 2022-01-25 | 天津大学 | Air particulate matter data monitoring system and method based on BP neural network |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040019155A1 (en) * | 2002-07-25 | 2004-01-29 | Mcleod Michael | Film clarity and rheological breadth in polyethylene resins |
| CN105406476A (en) * | 2015-12-31 | 2016-03-16 | 国家电网公司 | Historical data-based power system stability fast judging method |
-
2016
- 2016-06-20 CN CN201610446390.4A patent/CN106067079B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040019155A1 (en) * | 2002-07-25 | 2004-01-29 | Mcleod Michael | Film clarity and rheological breadth in polyethylene resins |
| CN105406476A (en) * | 2015-12-31 | 2016-03-16 | 国家电网公司 | Historical data-based power system stability fast judging method |
Non-Patent Citations (1)
| Title |
|---|
| 张怡文 等: "基于神经网络的PM2.5预测模型", 《江苏师范大学学报（自然科学版）》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108183928A (en) * | 2017-11-27 | 2018-06-19 | 易瓦特科技股份公司 | It is warned based on remote server the method, apparatus and system in gray haze source |
| CN108427905A (en) * | 2017-11-27 | 2018-08-21 | 易瓦特科技股份公司 | The method, apparatus and system warned to gray haze source based on remote server |
| CN110654202A (en) * | 2018-06-28 | 2020-01-07 | 大众汽车有限公司 | Ventilation of the interior of a vehicle |
| CN109242166A (en) * | 2018-08-25 | 2019-01-18 | 中科绿建（天津）科技发展有限公司 | A kind of environmental forecasting prevention and control system based on multiple dimensioned deep neural network |
| CN109363668A (en) * | 2018-09-03 | 2019-02-22 | 北京邮电大学 | Cerebral disease forecasting system |
| CN108872040A (en) * | 2018-09-30 | 2018-11-23 | 徐州工业职业技术学院 | A kind of city haze monitoring system |
| CN109492759A (en) * | 2018-12-17 | 2019-03-19 | 北京百度网讯科技有限公司 | Neural Network model predictive method, apparatus and terminal |
| CN110011994A (en) * | 2019-03-26 | 2019-07-12 | 惠州学院 | A kind of EMS based on big data |
| CN113067870A (en) * | 2021-03-18 | 2021-07-02 | 山东渤聚通云计算有限公司 | Device data processing method and device and server device |
| CN113219871A (en) * | 2021-05-07 | 2021-08-06 | 淮阴工学院 | Curing room environmental parameter detecting system |
| CN113970511A (en) * | 2021-10-21 | 2022-01-25 | 天津大学 | Air particulate matter data monitoring system and method based on BP neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106067079B (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106067079A (en) | A kind of system and method for gray haze based on BP neutral net prediction | |
| Ferrando et al. | Urban building energy modeling (UBEM) tools: A state-of-the-art review of bottom-up physics-based approaches | |
| Ali et al. | Review of urban building energy modeling (UBEM) approaches, methods and tools using qualitative and quantitative analysis | |
| Nagpal et al. | A methodology for auto-calibrating urban building energy models using surrogate modeling techniques | |
| WO2021238505A1 (en) | Federated learning-based regional photovoltaic power probability prediction method, and cooperative regulation and control system | |
| CN110766212B (en) | Ultra-short-term photovoltaic power prediction method for historical data missing electric field | |
| CN103279831B (en) | For the management system implementation method of evaluation software test mass and development ability | |
| CN106951611A (en) | A kind of severe cold area energy-saving design in construction optimization method based on user's behavior | |
| CN108197737A (en) | A kind of method and system for establishing medical insurance hospitalization cost prediction model | |
| CN109564579A (en) | The case where for Internet of Things integrated platform forecasting mechanism | |
| CN106022614A (en) | Data mining method of neural network based on nearest neighbor clustering | |
| CN101853290A (en) | Meteorological service performance evaluation method based on geographical information system (GIS) | |
| Feng et al. | Design and simulation of human resource allocation model based on double-cycle neural network | |
| Bian et al. | Abnormal detection of electricity consumption of user based on particle swarm optimization and long short term memory with the attention mechanism | |
| Liu et al. | Edge sensing data-imaging conversion scheme of load forecasting in smart grid | |
| CN108549907A (en) | A kind of data verification method based on multi-source transfer learning | |
| CN106771568B (en) | Area distribution formula photovoltaic stealing supervisory systems | |
| CN108416524A (en) | Estate planning based on a figure general framework refines deciphering method | |
| CN108475257A (en) | It handles far distance instrument and reads data to analyze consumption pattern | |
| CN116681177A (en) | Building energy saving method and system based on building energy consumption carbon integral reduction and prevention | |
| Li et al. | Privacy protection in prosumer energy management based on federated learning | |
| CN105005623A (en) | Power demand prediction method based on keyword retrieval index correlation analysis | |
| CN103870879A (en) | Method for selecting knowledge of computer-assisted decision making system based on undistinguishable relation | |
| CN104683144B (en) | A kind of internet of things equipment dependency degree evaluation method based on Markov model | |
| Połap et al. | Energy consumption prediction model for smart homes via decentralized federated learning with LSTM |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |