CN103942251A - Method and system for inputting high altitude meteorological data into database based on multiple quality control methods - Google Patents
Method and system for inputting high altitude meteorological data into database based on multiple quality control methods Download PDFInfo
- Publication number
- CN103942251A CN103942251A CN201410093749.5A CN201410093749A CN103942251A CN 103942251 A CN103942251 A CN 103942251A CN 201410093749 A CN201410093749 A CN 201410093749A CN 103942251 A CN103942251 A CN 103942251A
- Authority
- CN
- China
- Prior art keywords
- data
- quality control
- layer
- control method
- high altitude
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention discloses a method for inputting high altitude meteorological data into a database based on multiple quality control methods. The method includes the steps of data collection, data pre-processing, traditional quality control, quality control based on a data mining algorithm, quality control based on GIS spatial interpolation, quality control based on the chaos theory, data classification and data inputting in sequence. The invention further discloses a system for inputting the high altitude meteorological data into the database based on the multiple quality control methods. The system is of a four-layer architecture pattern and sequentially comprises an equipment layer, a communication analysis layer, a convergence processing layer and a presentation layer from the bottom layer to the top layer. The multiple data quality control methods are used comprehensively, a new data inputting technology is used in the system, in this way, quality of the high altitude data is improved, the guiding function on weather forecast and climatic prediction of the high altitude data after quality control is enhanced, representativeness and authority of the data are improved, and the efficiency of inputting the mass high altitude data into the database is improved by using the new data inputting technology.
Description
Technical field
The invention belongs to weather data observation field, particularly aerological data storage method and the Input System based on multiple quality control method.
Background technology
Aerological data are to make the basic data of weather forecast and climatic prediction, and its quality directly affects the correctness of weather forecast and climatic prediction.The robotization of station meteorological observation means and the lasting raising of data rate, the raising of observing frequency, the collected and transmission of mass data, preserves.Therefore, be very necessary with the method for quality control of confirmation and observational record marking error or suspicious efficiently fast, could, fast for user provides observation information as far as possible reliably, just can make forecaster make business as far as possible accurately and determine like this.The whether accurate development that directly affects meteorological cause of high-altitude data information, and aerological data are the most easily subject to the impact of observational error factor equipment state and artificial, so that the quality control of aerological data seems is particularly important.Along with the development that deepens continuously of cause of science, scientific worker is in the urgent need to higher-quality meteorological data.Upper air observation record must representative, accuracy, comparative.Yet meteorological data is subject to the impacts such as survey station position, surveying instrument, observation technology, observation time, observation procedure, especially aerological data, the impact that various non-meteorological factors cause is larger, meteorological data is had a greatly reduced quality, and the importance of the quality control of meteorological data has become all meteorological data scientific workers and has generally acknowledged.
The control of aerological data information and assessment business are of great significance guaranteeing integrality, reliability, the representative tool of weather data.Take data quality control and Input System as basic platform, by computer technology, realize quality control, assessment and the ordered series of numbers Homogeneity Test of all kinds of weather datas, mode with man-machine interaction realizes correcting of meteorological data, for country, provincial, and municipal level weather data memory scan provides accurately, standardization, authoritative weather data data.
Summary of the invention
The problem existing in order to solve above-mentioned background technology, the present invention aims to provide aerological data storage method and the Input System based on multiple quality control method, by the geopotential unit to high-altitude data, temperature, dew-point deficit, the key element Integrated using several data method of quality control such as wind are analyzed, and by new warehouse-in utilization in system, this not only can improve the quality of high-altitude data, the directive function of high-altitude data after enhancing Quality Control to weather forecast and climatic prediction, improve the representativeness of data, authoritative, and the use of newly putting technology in storage also will improve the efficiency of magnanimity high-altitude data loading.
In order to realize above-mentioned technical purpose, technical scheme of the present invention is:
Aerological data storage method based on multiple quality control method, comprises following steps:
The first step: data acquisition: the sensor by each automatic weather station gathers data;
Second step: data pre-service: the data that collect are carried out to rough error differentiation;
The 3rd step: use traditional quality control method deal with data: comprise successively the inspection of climatology boundary value, patrol
Collect inspection, internal consistency inspection, time consistency inspection, Space Consistency inspection;
The 4th step: use data mining algorithm based on BP neural network as Quality Control algorithm process data, it
Comprise the following steps:
Step 1: one group of weights of initialization and threshold value;
Step 2: all types of weather datas that a Meteorological Automatic Station is uploaded, as input data, along network forward-propagating, are calculated the actual output of current input pattern and the error delta of expecting output;
Step 3: if δ is less than set-point ξ, go to step 5, otherwise go to step 4;
Step 4: upgrade each node threshold value and weights, go to step afterwards 2;
Step 5: Output rusults, algorithm finishes;
The 5th step: use successively based on GIS space interpolation quality control method and the quality control method place based on chaology
Reason data;
The 6th step: Data classification: data are classified according to suspicious degree;
The 7th step: data loading: by data importing database.
Wherein, the rough error in above-mentioned second step is differentiated employing boundary value criterion or Xiao Weile diagnostic method or t check diagnostic method.
Wherein, the database in above-mentioned the 7th step adopts oracle database or Access or PostgreSQL.
The present invention includes for implementing the Input System of the above-mentioned aerological data storage method based on multiple quality control method, this system is four layer framework patterns, comprises the mechanical floor, communication analysis layer, convergence processing layer and the presentation layer that from bottom to top layer, connect successively; Described mechanical floor is realized the seamless access of each automatic weather station, described communication analysis layer realize automatic weather station and service center between data communication and parsing, and carry out data pre-service at this layer, described convergence processing layer realizes that the data that communication analysis layer is imported into are collected, quality control, Data classification and warehouse-in, and described presentation layer is realized the monitor record of data treatment state, data statistics, parameter management, DB Backup and file processing.
Wherein, between the said equipment layer and communication analysis layer, by GPRS or 3G/4G network, carry out telecommunication.
The beneficial effect that adopts technique scheme to bring is:
(1) the present invention, by multiple method of quality control for system, carries out quality control before aerological data loading, will greatly improve accuracy and representativeness into database data.
(2) the present invention classifies the data after Quality Control, is respectively A, B, and C, D class, each class represents different data dubieties, then according to the classification of data, data is carried out to overall treatment, clear thinking, processing is easily understood.
(3) the present invention breaks through common three-tier architecture pattern, and system divides is become to four levels, and every one deck all has peculiar work and attribute separately, and the framework layered effect of system is obvious.
Accompanying drawing explanation
Fig. 1 is the aerological data storage method process flow diagram based on multiple quality control method of the present invention;
Fig. 2 is the Input System structured flowchart for storage method shown in Fig. 1 of the present invention;
Fig. 3 is a kind of concrete Input System process flow diagram based on Fig. 2 of the present invention.
Embodiment
Below with reference to accompanying drawing, technical scheme of the present invention is elaborated.
Aerological data storage method process flow diagram based on multiple quality control method of the present invention as shown in Figure 1, comprises the following steps:
The first step: data acquisition: the sensor by each Meteorological Automatic Station gathers high-altitude data;
Second step: data pre-service: realize Meteorological Automatic Station is passed by GPRS communication network or alternate manner
The data that are delivered to weather bureau's central server are carried out rough error differentiation, if unusual error or the human error of data
Surpass threshold value, think and error in data operate otherwise carry out next step, this is the standard in early stage of quality control
Standby work;
The 3rd step: use traditional quality control method deal with data, step is as follows:
1, data are carried out to the inspection of climatology boundary value: this refers to the key element value that can not occur from climatology angle, if data in climatology boundary value, are carried out next step operation, otherwise think error in data;
2, data are carried out to logical check: the internal relations according to meteorological element between observation rule and meteorological element carries out logical check to observational record, and the content of its logical check comprises geopotential unit, temperature, dew-point deficit, wind etc.If the requirement of data fit logical check, carries out next step and checks, otherwise think that data are suspicious;
3, data are carried out to internal consistency inspection: the relation between the meteorological element record of same time observation must meet certain rule, if the inspection of data fit internal consistency is carried out next step operation, otherwise thought that data are suspicious;
4, data are carried out to time consistency inspection: meteorological record is changed and whether within the regular hour, changes and have specific rule, if the inspection of data fit time consistency is carried out next step operation, otherwise thought that data are suspicious;
5, data are carried out to Space Consistency inspection: meteorological element correlativity inspection spatially, have living space interpolation, space of main method returns inspection, climatic statistics relative method etc., if data fit Space Consistency checks, carry out next step operation, otherwise think that data are suspicious;
The 4th step: utilize data mining algorithm as quality control method deal with data, if next step operation is carried out in its requirement of data fit, otherwise think that data are suspicious.This algorithm has mainly been used BP neural network, and step is as follows:
1, one group of weights of initialization and threshold value;
2, input data, along network forward-propagating, are calculated the actual output of current input pattern and the error delta of expecting output;
If 3 δ are less than set-point ξ, go to step 5, otherwise go to step 4;
4, upgrade each node threshold value and weights, go to step afterwards 2;
5, Output rusults, algorithm finishes, and now to all sample trainings, the output of network model can meet the demands;
The false code of this algorithm is as follows:
Input: training sample temperature, comprises each training tuple and corresponding data set;
Output a: neural network training;
Init w
ij, θ
j(Random) // initialization weights and threshold value
While(predicated error δ >=set-point ξ or frequency of training≤predicted value)
{ // forward-propagating input process
Training sample temperature record in For inputs
{For?each?neuron?j?in?hidden?layer?and?output?layer
computing node j is about the clean input of front one deck i, and wherein Oi is the feature of i layer
} // use Sigmoid function is mapped to the output of each node j in the interval of [0,1], wherein O
jfor threshold function table;
The reverse communication process of // error
For?each?neuron?j?in?output?layer
E
j＝O
j*(1-O
j)*(T
j-O
j)
// according to true load value corresponding to known sample data, the error E of computing node j
j, T wherein
jthe real output of the known class label based on given training sample;
For?each?neuron?j?in?output?layer
E
j＝O
j*(1-O
j)*Σ(E
k*W
jk)
// according to the error that is connected to whole nodes of node j in next higher level, calculate the error E of this node
j, E wherein
kthe error of node k, W
jkbe in next higher level node k to the connection weight of node j;
Each connects weights W For network
ij{
ΔW
ij＝r*E
jO
j
W
ij←W
ij+VW
ij
} // right value update
For network node threshold value θ
j{
Vθ
j＝r*E
j
θ
j←θ
j+Vθ
j
} // threshold value is upgraded, and wherein r is learning rate
}
}
The 5th step: use based on GIS space interpolation quality control method and the quality control method deal with data based on chaology, if its requirement of data fit thinks that data are correct, otherwise think that data are suspicious
The 6th step: Data classification, the above-mentioned suspicious data of judging is classified by comprehensive distinguishing method, be divided into A level, B level, C level, D level, so-called comprehensive distinguishing method, preset exactly A level, B level, the C level of each every kind of data type in weather station, the critical field of D level, and these critical fields are encapsulated in dynamic link library, data are inputted this dynamic link library, data value and critical field are compared, just can draw the data level of self:
A level: it is misdata enough evidence proves, directly rejects;
B level: strong suspicious data is threat level data is rejected it from Service Database, as listing reference database preservation in reference to detecting data.
C level: suspicious data, data are more suspicious, but have certain confidence level, these type of data are only carried out to this locality and preserve, and do not report.
D level: weak suspicious data, data have suspicious, process, but will carry out weak suspicious remarks but can be used as trust data.
For implementing the Input System structured flowchart of above-mentioned storage method, this system is four layer framework patterns as shown in Figure 2, comprises the mechanical floor, communication analysis layer, convergence processing layer and the presentation layer that from bottom to top layer, connect successively.Wherein, mechanical floor and communication analysis layer carry out telecommunication by GPRS or 3G/4G network.Mechanical floor is realized the seamless access of each Meteorological Automatic Station, this layer of compatibility base station, basic station, general station, regional station and satellite communication station etc.Communication analysis layer plays the effect of forming a connecting link in whole system framework, realizes communicating by letter and parsing of Data of Automatic Weather and service center.Convergence processing layer is realized the data that communication analysis layer is imported into and is collected and carry out quality control, finally puts processing in storage.Presentation layer is realized the monitor record to data treatment state, data statistics, parameter management, DB Backup, file processing, file transfer.Data acquisition completes at mechanical floor, and data pre-service completes at communication analysis layer, and data Quality Control, classification and warehouse-in complete at convergence processing layer.
A kind of concrete Input System process flow diagram based on Fig. 2 as shown in Figure 3, first each meteorological site is made a report on high-altitude data message, data layout is EXCEL, then batch module of form being submitted to a higher level for approval or revision is examined, by province office, examined before this, by after report again State Bureau and examine, examine by data are reported and submitted to Quality Control module later, by Quality Control module, data are carried out to concrete quality control, finally the data that are disposed are submitted to into library module and put processing in storage.If have warning information warning information to be uploaded and be sent to the request of Quality Control module by SMS module, process, log pattern is that above-mentioned flow process is carried out to refinement record, authority module is upgraded user right by log recording, and the confirmation that user right upgrades result is fed back to and examines module.
Above embodiment only, for explanation technological thought of the present invention, can not limit protection scope of the present invention with this, every technological thought proposing according to the present invention, and any change of doing on technical scheme basis, within all falling into protection domain of the present invention.
Claims (5)
1. the aerological data storage method based on multiple quality control method, is characterized in that: comprise following steps:
The first step: data acquisition: the sensor by each automatic weather station gathers data;
Second step: data pre-service: the data that collect are carried out to rough error differentiation;
The 3rd step: use traditional quality control method deal with data: comprise successively the inspection of climatology boundary value, logical check, internal consistency inspection, time consistency inspection, Space Consistency inspection;
The 4th step: the data mining algorithm of use based on BP neural network is as Quality Control algorithm process data, and it comprises the following steps:
Step 1: one group of weights of initialization and threshold value;
Step 2: all kinds of weather datas that a Meteorological Automatic Station is uploaded, as input data, along network forward-propagating, are calculated the actual output of current input pattern and the error of expecting output;
Step 3: if the error that step 2 is calculated is less than set-point, goes to step 5, otherwise go to step 4;
Step 4: upgrade each node threshold value and weights, go to step afterwards 2;
Step 5: Output rusults, algorithm finishes;
The 5th step: use successively based on GIS space interpolation quality control method and the quality control method deal with data based on chaology;
The 6th step: Data classification: data are classified by comprehensive distinguishing method;
The 7th step: data loading: by data importing database.
2. the aerological data storage method based on multiple quality control method according to claim 1, is characterized in that: the rough error in described second step is differentiated and adopted boundary value criterion or Xiao Weile diagnostic method or t check diagnostic method.
3. the aerological data storage method based on multiple quality control method according to claim 1, is characterized in that: the database in described the 7th step adopts oracle database or Access or PostgreSQL.
4. for implementing the claims the Input System of the aerological data storage method based on multiple quality control method described in 1, it is characterized in that: this system is four layer framework patterns, comprise the mechanical floor, communication analysis layer, convergence processing layer and the presentation layer that from bottom to top layer, connect successively; Described mechanical floor is realized the seamless access of each automatic weather station, described communication analysis layer realize automatic weather station and service center between data communication and parsing, and carry out data pre-service at this layer, described convergence processing layer realizes that the data that communication analysis layer is imported into are collected, quality control, Data classification and warehouse-in, and described presentation layer is realized the monitor record of data treatment state, data statistics, parameter management, DB Backup and file processing.
5. according to claim 4 for implementing the claims the Input System of the aerological data storage method based on multiple quality control method described in 1, it is characterized in that: between described mechanical floor and communication analysis layer, by GPRS or 3G/4G network, carry out telecommunication.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410093749.5A CN103942251A (en) | 2014-03-13 | 2014-03-13 | Method and system for inputting high altitude meteorological data into database based on multiple quality control methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410093749.5A CN103942251A (en) | 2014-03-13 | 2014-03-13 | Method and system for inputting high altitude meteorological data into database based on multiple quality control methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103942251A true CN103942251A (en) | 2014-07-23 |
Family
ID=51189919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410093749.5A Pending CN103942251A (en) | 2014-03-13 | 2014-03-13 | Method and system for inputting high altitude meteorological data into database based on multiple quality control methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103942251A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105809321A (en) * | 2016-01-26 | 2016-07-27 | 南京信息工程大学 | Quality control method of temperature data acquired by ground meteorological observation station |
| CN106096266A (en) * | 2016-06-08 | 2016-11-09 | 南京信息工程大学 | A kind of automatic weather station method of quality control |
| CN106919645A (en) * | 2017-01-17 | 2017-07-04 | 广西师范学院 | The sight spot meteorological element Intelligent fine Forecasting Methodology at the big scenic spot of complex landform |
| CN108038087A (en) * | 2017-12-29 | 2018-05-15 | 浙江省公众信息产业有限公司 | Water and fertilizer irrigation decision-making technique, device and system, computer-readable recording medium |
| CN112559588A (en) * | 2020-12-08 | 2021-03-26 | 天津市气象信息中心(天津市气象档案馆) | Construction method of one-hundred-year uniform air temperature daily value sequence observed by ground meteorological station |
| CN115599869A (en) * | 2022-12-14 | 2023-01-13 | 联仁健康医疗大数据科技股份有限公司（Cn） | Data acquisition method and device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030023534A1 (en) * | 2001-06-11 | 2003-01-30 | Shubha Kadambe | Method and apparatus for determining and assessing information to be collected based on information-theoretic measures |
| CN102081764A (en) * | 2011-01-11 | 2011-06-01 | 上海海洋大学 | ULDB (Databases with Uncertainty and Lineage)-based marine environmental monitored data management system |
-
2014
- 2014-03-13 CN CN201410093749.5A patent/CN103942251A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030023534A1 (en) * | 2001-06-11 | 2003-01-30 | Shubha Kadambe | Method and apparatus for determining and assessing information to be collected based on information-theoretic measures |
| CN102081764A (en) * | 2011-01-11 | 2011-06-01 | 上海海洋大学 | ULDB (Databases with Uncertainty and Lineage)-based marine environmental monitored data management system |
Non-Patent Citations (2)
| Title |
|---|
| 孙娓娓: "BP神经网络的算法改进及应用研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 沈军: "气象自动观测站数据处理方法研究", 《中国博士学位论文全文数据库 基础科学辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105809321A (en) * | 2016-01-26 | 2016-07-27 | 南京信息工程大学 | Quality control method of temperature data acquired by ground meteorological observation station |
| CN106096266A (en) * | 2016-06-08 | 2016-11-09 | 南京信息工程大学 | A kind of automatic weather station method of quality control |
| CN106919645A (en) * | 2017-01-17 | 2017-07-04 | 广西师范学院 | The sight spot meteorological element Intelligent fine Forecasting Methodology at the big scenic spot of complex landform |
| CN108038087A (en) * | 2017-12-29 | 2018-05-15 | 浙江省公众信息产业有限公司 | Water and fertilizer irrigation decision-making technique, device and system, computer-readable recording medium |
| CN108038087B (en) * | 2017-12-29 | 2021-02-02 | 浙江省公众信息产业有限公司 | Water and fertilizer irrigation decision method, device and system and computer readable storage medium |
| CN112559588A (en) * | 2020-12-08 | 2021-03-26 | 天津市气象信息中心(天津市气象档案馆) | Construction method of one-hundred-year uniform air temperature daily value sequence observed by ground meteorological station |
| CN112559588B (en) * | 2020-12-08 | 2023-01-24 | 天津市气象信息中心(天津市气象档案馆) | Construction method of one-hundred-year uniform air temperature daily value sequence observed by ground meteorological station |
| CN115599869A (en) * | 2022-12-14 | 2023-01-13 | 联仁健康医疗大数据科技股份有限公司（Cn） | Data acquisition method and device, electronic equipment and storage medium |
| CN115599869B (en) * | 2022-12-14 | 2023-03-14 | 联仁健康医疗大数据科技股份有限公司 | Data acquisition method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103942251A (en) | Method and system for inputting high altitude meteorological data into database based on multiple quality control methods | |
| CN107169628B (en) | Power distribution network reliability assessment method based on big data mutual information attribute reduction | |
| CN103745229A (en) | Method and system of fault diagnosis of rail transit based on SVM (Support Vector Machine) | |
| CN105574593B (en) | Track state static detection and control system and method based on cloud computing and big data | |
| CN107766879A (en) | The MLP electric network fault cause diagnosis methods of feature based information extraction | |
| CN110457829A (en) | A kind of source item release inverting and DIFFUSION PREDICTION method based on integrated model of atmospheric diffusion | |
| CN101853290A (en) | Meteorological service performance evaluation method based on geographical information system (GIS) | |
| CN114493052B (en) | Multi-model fusion self-adaptive new energy power prediction method and system | |
| Chen et al. | Vulnerability modeling, assessment, and improvement in urban metro systems: A probabilistic system dynamics approach | |
| CN111882202A (en) | Group building synchronous construction risk management system based on BP neural network | |
| CN110866775A (en) | User air-rail joint inter-city trip information processing method based on machine learning | |
| CN115271373A (en) | Method and system for defining elastic development boundary of urban group | |
| CN106779222A (en) | Airport ground stand-by period Forecasting Methodology and device | |
| CN110472866A (en) | A kind of work order quality inspection analysis method and device | |
| CN107229916A (en) | A kind of airport noise Monitoring Data restorative procedure based on depth noise reduction own coding | |
| CN117036112B (en) | Geographic information system and method for land planning | |
| CN107145995A (en) | Production environment safety prediction methods, devices and systems | |
| CN111709597B (en) | Power grid production domain operation monitoring system | |
| CN115792505B (en) | Rail transit power supply management method and system | |
| CN107392506A (en) | A kind of self-study line status evaluation system and evaluation method for merging development of Mobile Internet technology | |
| CN112836843A (en) | Method and device for predicting base station out-of-service alarm | |
| CN115659214A (en) | Energy industry data credible evaluation method based on PaaS platform | |
| CN113361730B (en) | Risk early warning method, device, equipment and medium for maintenance plan | |
| CN114880954A (en) | Landslide sensitivity evaluation method based on machine learning | |
| Xiao-Xu et al. | An intelligent inspection robot of power distribution network based on image automatic recognition system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140723 |
|
| RJ01 | Rejection of invention patent application after publication |