CN106067079B - System and method for predicting dust haze based on BP neural network - Google Patents
System and method for predicting dust haze based on BP neural network Download PDFInfo
- Publication number
- CN106067079B CN106067079B CN201610446390.4A CN201610446390A CN106067079B CN 106067079 B CN106067079 B CN 106067079B CN 201610446390 A CN201610446390 A CN 201610446390A CN 106067079 B CN106067079 B CN 106067079B
- Authority
- CN
- China
- Prior art keywords
- haze
- dust
- data
- prediction
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- 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 a system and a method for predicting dust haze based on a BP neural network, wherein the system comprises: mining the relation between the collected air quality data through a BP neural network, predicting the air quality and the development trend of dust-haze weather, and providing early warning for the dust-haze weather; the method is characterized in that: the system comprises a data acquisition module, a database, a data sorting module, a dust-haze prediction server, a data preprocessing module, a neuron learning module, a BP neural network prediction module, a WEB server and a mobile terminal; the method comprises the following steps: describing the dust-haze prediction system as a multi-input multi-output self-learning prediction system, inputting collected dust-haze and air quality data, predicting the possible development trend of dust-haze weather through the self-learning and self-adaptive capacity of a neural network, and reducing prediction errors; the method can predict the development of the dust haze by utilizing the existing dust haze observation data, can deeply mine the complex relation among the input data, and obtains a more accurate prediction effect.
Description
Technical Field
The invention relates to a dust-haze prediction method and technology, in particular to a system and method for predicting dust-haze based on a BP neural network.
Background
At present, the dust-haze phenomenon in China is more and more concerned, and researches on prediction analysis and treatment strategies of dust-haze are more and more endless, while the currently established dust-haze prediction analysis technology mainly comprises the aspects of dust-haze monitoring, dust-haze assessment, strategy prediction, strategy implementation and the like. The existing dust-haze prediction method and system mainly use ecological environment and air quality index monitoring as main modeling, use the monitored indexes such as PM2.5 and PM1.0 to try to accurately describe a dust-haze mathematical model and an evolution mechanism, and the latest technology also comprises technologies such as sensor network arrangement in a dust-haze frequent region and satellite image analysis, so that a large amount of accurate data are provided for dust-haze monitoring and early warning, and then, the development trend of dust-haze is analyzed and predicted according to the method, so that relevant dust-haze prevention measures are made.
The existing haze prediction analysis method and system have obvious defects, and mathematical functions need to be established for different data, including PM2.5, PM1.0 particulate matters, carbon dioxide, nitrogen dioxide, sulfur monoxide and the like, and entities with different properties are different in calculation. In addition, the development and prediction of the dust haze are also closely related to local geographic environment and production life, and interference situations among different data must be considered according to the data for predicting the dust haze. Moreover, the natural environment and the social environment where the dust haze is located have self-learning properties, and the traditional prediction method is difficult to consider. In China, with the application of a data processing technology in dust-haze prediction, conditions are provided for predicting dust-haze by using a data acquisition and self-learning method, but few dust-haze prediction methods and systems based on a BP (back propagation) neural network are available in the market at present.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a system and a method for predicting the dust haze based on a BP (back propagation) neural network, which are used for mining the relation among various data related to the dust haze and a self-learning mechanism through the BP neural network and providing data support for prediction and decision of the dust haze.
The technical scheme adopted by the invention is as follows:
a system for predicting dust and haze based on a BP neural network comprises a data acquisition module, a dust and haze database, a dust and haze prediction server, a WEB server and a mobile terminal. The data acquisition module is connected with the dust-haze database, the dust-haze database is connected with the dust-haze prediction server, and the dust-haze prediction server is respectively connected with the WEB server and the mobile terminal.
The data acquisition module: the data acquisition module will acquire the data relevant with the dust haze through various sensors and monitoring equipment, deposit the data of collecting in the dust haze database.
The data acquisition module: the collected data information must be collected and input uniformly by national environment, statistics and other departments, so that the accuracy of information sources is ensured.
Dust haze database: the device is used for storing data of inhalable particles, sulfur dioxide, nitrogen oxides and the like related to dust and haze;
dust haze database: the system is released, managed and updated by a China meteorological department or a dust-haze authority, collected data are stored in a database, and the collected data are transmitted to a dust-haze prediction server after being sorted by necessary data.
The dust-haze database comprises a data sorting module, the data sorting module sorts and summarizes data collected by the data collecting module, the data can be from different databases or data sets, the data are usually incomplete, missing and noisy, the input of the low-quality data cannot obtain a high-quality prediction result, and the data sorting is needed so as to be centralized in the dust-haze database;
the data sorting module: and (4) for different data, adopting different data processing methods so as to arrange the data into a uniform format and store the uniform format in a dust-haze database.
The haze prediction server: taking out data in a dust-haze database, carrying out data preprocessing and initialization of input and output data, setting training parameters of a BP neural network, learning and fitting a function curve by neurons, comparing a predicted value with an actual value, continuously correcting the current input amount until a training error is lower than a set value, and finally outputting a predicted amount;
the haze prediction server: the method comprises a neuron learning method which operates stably, has small error, is rapid and convenient, and can display and send the final prediction result to the mobile terminal in a network mode.
The gray haze prediction server comprises a data preprocessing module, a neuron training module and a BP neural network prediction module.
The data preprocessing module: carrying out normalization processing on data taken out of the dust-haze database to enable the data to be distributed between-1 to +1, and preparing high-quality data for neuron learning training;
the gray haze prediction server comprises methods of simple scaling, sample-by-sample mean reduction, characteristic standardization and the like, and the BP algorithm can exert the best prediction effect through preprocessing.
After the training parameters are set, the neuron training module corrects the network weight coefficient by self-learning and utilizing the error between the actual output and the expected output, and finally outputs the optimal prediction effect;
the neuron training module further comprises: the neuron self-learns and self-adaptively adjusts the learning step length to finish the forward propagation of information and the backward propagation of errors
The neuron training module comprises a BP algorithm, and the BP algorithm has good convergence characteristics, good self-learning and self-adaption capabilities and good fault-tolerant capability.
And the BP neural network prediction module outputs a neuron prediction result and performs inverse normalization on the data to obtain data under the same index as the original data.
And the BP neural network prediction module inputs the prediction result into a WEB server and a mobile terminal, and timely and efficiently performs dust-haze early warning.
The WEB server: the development trend of the dust haze can be predicted, the prediction result is converted into the forms of charts, line graphs and the like, and the charts, the line graphs and the like are sent to relevant meteorological departments;
the WEB server: and (4) corresponding the prediction result to the dust haze of each grade, making corresponding early warning according to the dust haze index condition, and making a corresponding dust haze treatment strategy.
The mobile terminal: and converting the prediction result into an air quality index or chart and a prediction result line chart, and sending the air quality index or chart and the prediction result line chart to the hand of the mobile terminal user to provide a suggestion for the user to go out.
The mobile terminal: the user can inquire the relevant index condition of the dust-haze in real time, the mobile terminal provides corresponding suggestions for the user about to go out, and the user is reminded conveniently and quickly.
The invention discloses a system and a method for predicting dust haze based on a BP neural network, which have the following advantages:
1: firstly, the dust-haze prediction system is modeled into a multi-input multi-output system, and PM2.5 and PM1.0 materials, carbon dioxide, nitrogen dioxide, sulfur monoxide and the like can be calculated according to entities with different attributes.
2: secondly, calculation can be carried out according to local geography and production and life data, interference conditions among different data are considered, prediction is given after actual conditions are combined, and accuracy of dust-haze prediction is improved.
3: and thirdly, the method has self-learning characteristics, and can consider the self-learning characteristics of systems such as production, life, environment and the like, so that the parameters and training of the neurons and the neural network are adjusted according to the input of external data, and an optimization and solution method is provided.
4: the method describes the dust-haze prediction system as a multi-input multi-output self-learning prediction system, inputs collected dust-haze and air quality data, predicts the possible development trend of dust-haze weather through the self-learning and self-adaptive capacity of the neural network, and reduces prediction errors; the method can predict the development of the dust haze by utilizing the existing dust haze observation data, and can deeply mine the complex relation among the input data to obtain a more accurate treatment scheme.
Drawings
FIG. 1 is a schematic diagram of the present invention.
Fig. 2 is a flow chart of the algorithm of the present invention.
FIG. 3 is a graph of the predicted results of the present invention.
Detailed Description
As shown in fig. 1, a system for gray-haze prediction based on a BP neural network includes the following modules: the system comprises a data acquisition module 100, a database 101, a data sorting module 102, a haze prediction server 103, a data preprocessing module 104, a neuron learning module 105, a BP neural network prediction module 106, a WEB server 107 and a mobile terminal 108.
The system describes the gray haze prediction method as a multi-input multi-output neural network prediction system, and predicts the possible development trend of the gray haze through a self-learning mechanism of neurons; internal relations existing between input and output data are mined through a BP neural network model, incidence relations between the input data are continuously fitted, prediction errors are reduced through continuous feedback and a learning mechanism, and reference is provided for dust haze prevention and control.
The data acquisition module 100 comprises various sensors and monitoring equipment, is installed in various local environment systems, acquires data related to dust and haze, and stores the collected data into a dust and haze database; according to the data acquisition module 100, acquired data information must be uniformly acquired and input by national environment, statistics and other departments, so that the accuracy of information sources is ensured.
The dust-haze database 101 comprises a high-performance database and a storage module, is arranged in a data center of an environmental monitoring department, and is used for storing data such as inhalable particles, sulfur dioxide and nitrogen oxides related to dust and haze; the dust-haze database 101 is issued, managed and updated by a China meteorological department or a dust-haze authority, collected data is stored in the database, and the collected data is transmitted to the dust-haze prediction server 103 after being sorted by necessary data.
The data sorting module 102 is installed on a server, and comprises a background algorithm and an interface display, and is used for sorting and summarizing data collected by the data collection module 100, wherein the data may be from different databases or data sets, the data is usually incomplete, missing and noisy, such low-quality data input cannot obtain a high-quality prediction result, and the data sorting is required so as to be centralized in the haze database 100; the data sorting module 102 adopts different data processing methods for different data so as to sort the data into a uniform format and store the uniform format in the haze database 101.
The dust haze prediction server 103 is a high-performance server, is installed in an environment monitoring department, takes out data in the dust haze database 101, performs data preprocessing and initialization of input and output data, sets training parameters of a BP (back propagation) neural network, learns and fits a function curve, compares a predicted value with an actual value, continuously corrects the current input amount until a training error is lower than a set value, and finally outputs a predicted amount. The haze prediction server 103 can respond to the haze prediction and query requests of the user, has a stable neuron learning method, and displays and sends the final prediction result to the mobile terminal in a network mode.
The data preprocessing module 104 is installed on the server, and is used for performing normalization processing on the data taken out of the dust-haze database 101, so that the data are distributed between [ -1 to +1], and high-quality data are prepared for neuron learning training.
The neuron training module 105 is installed on a server, after training parameters are set, the neurons correct network weight coefficients by self-learning and utilizing errors between actual output and expected output, and finally output the best prediction effect.
The BP neural network prediction module 1 outputs the neuron prediction result, and simultaneously performs inverse normalization on the data to obtain the data under the same index as the original data. And the BP neural network prediction module 106 inputs the prediction result into the WEB server 107 and the mobile terminal 108, and timely and efficiently performs dust-haze early warning.
The WEB server 107 is installed in environment monitoring departments and users in various regions, can predict the development trend of dust haze, converts the prediction result into the forms of charts, line graphs and the like, and sends the charts, line graphs and the like to relevant meteorological departments. The WEB server 107 corresponds the prediction result to the dust haze of each grade, makes corresponding early warning according to the dust haze index condition, and formulates a corresponding dust haze treatment strategy.
The mobile terminal 108: and converting the prediction result into an air quality index or chart and a prediction result line chart, and sending the air quality index or chart and the prediction result line chart to the hand of the mobile terminal user to provide a suggestion for the user to go out. The user can inquire the relevant index condition of the dust-haze in real time, the mobile terminal provides corresponding suggestions for the user about to go out, and the user is reminded conveniently and quickly.
As shown in fig. 2, the algorithm flowchart of the gray-haze prediction method based on the BP neural network provided by the embodiment of the present invention is characterized by including a module for collecting gray-haze data and performing normalization processing, giving input and output vectors, calculating an output result, an expected value output and an actual deviation, and predicting a gray-haze index if an error meets a calculation end condition. According to the neuron training and the working process, the method comprises the steps of neuron self-learning, self-adaptive adjustment of learning step length and completion of forward propagation of information and backward propagation of errors. According to the algorithm process, the method is characterized in that the BP algorithm has good convergence characteristics, good self-learning and self-adaption capabilities and good fault-tolerant capability.
As shown in fig. 3, a prediction result diagram of the gray haze prediction method based on the BP neural network provided by the embodiment of the present invention can conform to actual data. According to the prediction algorithm process, the method comprises the methods of simple scaling, sample-by-sample mean reduction, feature standardization and the like, and the BP algorithm can exert the optimal prediction effect through preprocessing.
In fig. 3, it can be seen that the dispersion of the air quality data (such as the data points in fig. 3) is relatively large, and it has been difficult to accurately predict the air quality data, which is always the difficulty of environmental prediction and air quality prediction. The method can calculate and accurately predict PM2.5 and PM1.0 particles, carbon dioxide, nitrogen dioxide, sulfur monoxide and the like, and entities with different attributes (such as Fit curves in figure 3). Furthermore, the method can calculate data of systems such as production, life, environment and the like and perform self-learning, so that a targeted treatment scheme is obtained.
The above embodiments are only for illustrating the invention and are not to be construed as limiting the invention, and those skilled in the art can make various changes and modifications without departing from the precision and scope of the invention, so that all equivalent technical solutions also belong to the scope of the invention, and the scope of the invention is defined by the claims.
Claims (1)
1. A system for predicting dust and haze based on a BP neural network comprises a data acquisition module (100), a dust and haze database (101), a dust and haze prediction server (103), a WEB server (107) and a mobile terminal (108);
the data acquisition module (100) is connected with the dust-haze database (101), the dust-haze database (101) is connected with the dust-haze prediction server (103), and the dust-haze prediction server (103) is respectively connected with the WEB server (107) and the mobile terminal (108); the method is characterized in that: the data acquisition module (100) acquires data related to dust and haze through various sensors and monitoring equipment, and stores the collected data into a dust and haze database (101);
the dust-haze database (101) is used for storing data of inhalable particles, sulfur dioxide and nitrogen oxides related to dust and haze;
the dust-haze prediction server (103) is used for taking out data in the dust-haze database (101), carrying out data preprocessing and initialization of input and output data, setting training parameters of a BP neural network, learning and fitting a function curve by neurons, comparing a predicted value with an actual value, continuously correcting the current input quantity until a training error is lower than a set value, and finally outputting a predicted quantity;
the WEB server (107) is used for enabling the prediction result to correspond to the dust haze of each grade, making corresponding early warning according to the dust haze index condition and making a corresponding dust haze treatment strategy;
the mobile terminal (108) is used for converting the prediction result into an air quality index or chart and a prediction result line chart, sending the air quality index or chart and the prediction result line chart to the hand of a mobile terminal user and providing a suggestion for the user to go out;
the data acquisition module (100) is used for uniformly acquiring and inputting acquired data information by a national environment and a statistical department; the data acquisition module (100) is issued, managed and updated by a China meteorological department or a dust-haze authority, stores the collected data into a dust-haze database (101), and transmits the collected data to a dust-haze prediction server (103) after data arrangement;
the dust-haze database (101) comprises a data sorting module (102), the data sorting module (102) sorts and summarizes data collected by the data collecting module (100), and the data are from different databases or data sets;
the data sorting module (102) is used for sorting different data into a uniform format by adopting different data processing methods and storing the uniform format in the dust-haze database (101);
the haze prediction server (103) comprises a data preprocessing module (104), a neuron training module (105) and a BP neural network prediction module (106);
after the training parameters are set by the neuron training module (105), correcting the network weight coefficient by the neuron through self-learning by using the error between actual output and expected output, and finally outputting the optimal prediction effect;
the BP neural network prediction module (106) is used for outputting a neuron prediction result and performing inverse normalization on data to obtain data under the same index as the original data; the BP neural network prediction module (106) inputs the prediction result into a WEB server (107) and a mobile terminal (108);
the WEB server (107) is used for predicting the development trend of the dust haze, converting the prediction result into a chart and line graph form, forming a report and sending the report to a relevant meteorological department;
the data preprocessing module (104) is used for carrying out normalization processing on the data taken out of the dust-haze database (101) so that the data are distributed between [ -1 to +1 ];
internal relations existing between input and output data are mined through a BP neural network model, incidence relations between the input data are fitted continuously, prediction errors are reduced through continuous feedback and a learning mechanism, and reference is provided for dust haze prevention and control;
the system for predicting the dust haze can realize a method for predicting the dust haze, and the method for predicting the dust haze comprises the following steps:
collecting dust-haze data and carrying out normalization processing, giving input and output vectors, calculating an output result, an expected value output and an actual deviation, judging whether an error meets a calculation end condition or not, and predicting a dust-haze index;
the method for predicting the dust haze can calculate data of production, life and environment systems and perform self-learning, so that a targeted treatment scheme is obtained;
the method comprises the following steps of neuron training and a working process, wherein the process comprises neuron self-learning, self-adaptive adjustment of learning step length and completion of forward propagation of information and backward propagation of errors;
the dust-haze forecasting system is described as a multi-input multi-output self-learning forecasting system, collected dust-haze and air quality data are input, the possible development trend of dust-haze weather is forecasted through the self-learning and self-adaptive capacity of the neural network, and forecasting errors are reduced.
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 CN106067079A (en) | 2016-11-02 |
| CN106067079B true 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) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| DE102018210587A1 (en) * | 2018-06-28 | 2020-01-02 | Volkswagen Aktiengesellschaft | Ventilate an interior of a vehicle |
| CN109242166B (en) * | 2018-08-25 | 2021-05-04 | 臻儒(天津)科技有限公司 | Environmental prediction prevention and control system based on multi-scale 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 |
| CN109492759B (en) * | 2018-12-17 | 2022-05-20 | 北京百度网讯科技有限公司 | Neural network model prediction method, device 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 |
| CN113219871B (en) * | 2021-05-07 | 2022-04-01 | 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 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6914113B2 (en) * | 2002-07-25 | 2005-07-05 | Fina Technology, Inc. | Film clarity and rheological breadth in polyethylene resins |
| CN105406476B (en) * | 2015-12-31 | 2017-10-13 | 国家电网公司 | Stability of power system quick judgment method based on historical data |
-
2016
- 2016-06-20 CN CN201610446390.4A patent/CN106067079B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106067079A (en) | 2016-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106067079B (en) | System and method for predicting dust haze based on BP neural network | |
| Lindemann et al. | Anomaly detection and prediction in discrete manufacturing based on cooperative LSTM networks | |
| CN110376003B (en) | Intelligent train service life prediction method and system based on BIM | |
| CN110119845A (en) | A kind of application method of track traffic for passenger flow prediction | |
| CN112036075A (en) | Abnormal data judgment method based on environmental monitoring data association relation | |
| CN110361180B (en) | Intelligent train pantograph service performance dynamic monitoring and evaluating method and system | |
| CN110533239B (en) | Smart city air quality high-precision measurement method | |
| CN110363355B (en) | Cloud-edge collaborative forecasting system and method for alumina production index | |
| CN115759488B (en) | Carbon emission monitoring early warning analysis system and method based on edge calculation | |
| CN110555551A (en) | air quality big data management method and system for smart city | |
| US11842301B1 (en) | Methods for monitoring distributed energy storage safety and internet of things systems thereof | |
| CN116029435B (en) | Environmental comfort early warning system is bred to live pig facility | |
| CN112363896A (en) | Log anomaly detection system | |
| CN112270429A (en) | Cloud edge cooperation-based power battery pole piece manufacturing equipment maintenance method and system | |
| CN116167531A (en) | Photovoltaic power generation prediction method based on digital twin | |
| CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
| CN114118982A (en) | Cloud computing and edge computing combined production control system | |
| CN114564513A (en) | Sea fog prediction method, device, equipment and storage medium based on neural network | |
| CN112541633A (en) | Ultrahigh-precision photovoltaic power generation power prediction method and system based on neural network | |
| CN116225102B (en) | Mobile energy storage communication temperature rise automatic monitoring system and device | |
| CN116070669B (en) | Workshop energy consumption prediction method and management system based on improved deep belief network | |
| CN108345996B (en) | System and method for reducing wind power assessment electric quantity | |
| CN108134687B (en) | Gray model local area network peak flow prediction method based on Markov chain | |
| CN115481815A (en) | Thermal power plant load distribution system and method based on neural network | |
| CN115905348A (en) | Industrial electricity utilization abnormity early warning method and system of multi-source heterogeneous data |
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 |