CN111860562A - Self-adaptive dry-wet distinguishing method based on multiple statistics of microwave link - Google Patents

Self-adaptive dry-wet distinguishing method based on multiple statistics of microwave link Download PDF

Info

Publication number
CN111860562A
CN111860562A CN202010236872.3A CN202010236872A CN111860562A CN 111860562 A CN111860562 A CN 111860562A CN 202010236872 A CN202010236872 A CN 202010236872A CN 111860562 A CN111860562 A CN 111860562A
Authority
CN
China
Prior art keywords
wet
dry
microwave link
method based
adaptive
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
Application number
CN202010236872.3A
Other languages
Chinese (zh)
Other versions
CN111860562B (en
Inventor
刘西川
宋堃
贺彬晟
胡帅
高太长
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
National University of Defense Technology
Original Assignee
National University of Defense Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by National University of Defense Technology filed Critical National University of Defense Technology
Priority to CN202010236872.3A priority Critical patent/CN111860562B/en
Publication of CN111860562A publication Critical patent/CN111860562A/en
Application granted granted Critical
Publication of CN111860562B publication Critical patent/CN111860562B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01W—METEOROLOGY
    • G01W1/00—Meteorology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Environmental & Geological Engineering (AREA)
  • Atmospheric Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Ecology (AREA)
  • Environmental Sciences (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The invention discloses a self-adaptive dry and wet distinguishing method based on multiple statistics of a microwave link, which analyzes the correlation degree of statistical parameters of link attenuation data and dry and wet moments by adopting a statistical means, adaptively selects the statistical parameters with high correlation degree as characteristic vectors by taking the correlation degree as a criterion, and realizes the dry and wet distinguishing in the weather change process by utilizing a classification algorithm such as a support vector machine. The self-adaptive dry and wet distinguishing method can distinguish dry and wet moments by using the microwave link signal change, can effectively realize continuous monitoring of weather, and has important significance for further improving the precision of the microwave link rain measurement, improving the application benefit of the microwave link rain measurement method and the like.

Description

Self-adaptive dry-wet distinguishing method based on multiple statistics of microwave link
Technical Field
The invention relates to the field of meteorological information processing and application, in particular to a self-adaptive dry-wet distinguishing method based on microwave link multi-statistic.
Background
As one of the most active weather phenomena in the troposphere closely related to the lives of people, the precipitation phenomenon is closely related to the lives of people, and with the continuous development of various weather hydrologic related services, not only in the meteorological field, but also in more and more fields, higher and higher demands are made on acquiring precipitation related information. Meanwhile, under the trend that the meteorological guarantee becomes more and more refined, people have higher requirements on the quality of rainfall information. Therefore, the method has important significance in real-time, accurate and fine monitoring of rainfall, both in meteorological hydrology research and government early warning decision
In recent years, measures for measuring precipitation by using attenuation information in microwave frequency band communication signals are proposed, the distribution range of microwave signal base stations is wider along with the development of the communication field, and under the condition that special meteorological equipment is lacked, the cost can be greatly saved by using signal change information of the signal transceiver stations to monitor precipitation in a wide range. At present, interference factors in a plurality of microwave signals, such as interference of a wet antenna effect, multi-scale disturbance of the signals, irregular time distribution of reference baselines in level signals and the like, are common in commercial microwave links, and the application of the microwave links in monitoring precipitation is limited.
Disclosure of Invention
The purpose of the invention is as follows: the invention provides a self-adaptive dry and wet distinguishing method based on multiple statistics of a microwave link, aiming at the problems that a large part of communication link receiving signals have a complex time distribution rule, and the dry and wet moments are difficult to distinguish accurately, so that a rain attenuation reference value is difficult to extract accurately and the inversion accuracy of rain intensity is limited.
The technical scheme is as follows: in order to achieve the purpose, the invention adopts the technical scheme that:
a self-adaptive dry and wet distinguishing method based on multiple statistics of a microwave link analyzes the correlation degree of statistical parameters of link attenuation data and dry and wet moments by adopting a statistical means, adaptively selects the statistical parameters with high correlation degree as characteristic vectors by taking the correlation degree as a criterion, and realizes the dry and wet distinguishing in the weather change process by utilizing a classification algorithm such as a support vector machine, and the method specifically comprises the following steps:
step 1: analyzing the correlation degree of the microwave link signal attenuation data and the dry and wet time:
and 1.1, calculating statistical parameters of microwave link signals.
And step 1.2, selecting statistical parameters with high correlation degree with the dry and wet time to form a feature vector of a support vector machine classification algorithm.
Step 2: selecting an effective microwave link: and selecting the link with high correlation degree to distinguish the dry state from the wet state by taking the correlation between the link attenuation data and the dry state as an index.
And step 3: establishing a self-adaptive dry-wet distinguishing method based on multiple statistics of a microwave link:
step 3.1, forming a training data set x by using historical observation dataT,iAnd yT,i，xT,iIs a feature vector consisting of statistical parameters, y T,iDry and wet label values.
Step 3.2, constructing and solving an optimal solution of the convex quadratic programming problem:
Figure RE-GDA0002680548790000021
Figure RE-GDA0002680548790000022
solving the above equation to obtain alpha*Where K (. cndot.) is a kernel function, α*Represents the optimal solution of convex quadratic problem, N represents the number of training set samples, alphaiRepresenting the Lagrangian multiplier, yT,iIndicating a dry-wet label, C indicating a penalty parameter, taking the value as>0。
Step 3.3, calculating to obtain a weight vector w of the classification function*：
Figure RE-GDA0002680548790000023
Step 3.4, calculating a classification function weight vector b:
Figure RE-GDA0002680548790000024
step 3.5, constructing a classification function:
Figure RE-GDA0002680548790000025
wherein the content of the first and second substances,
Figure RE-GDA0002680548790000026
representing the optimal solution of the convex quadratic problem.
Preferably: the statistical parameters comprise an attenuation mean value, a minimum value and a maximum value of the microwave link signal.
Preferably: when f (x) is 1, the classification result is the wet time, and when f (x) is-1, the classification result is the dry time.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a self-adaptive dry and wet distinguishing method based on multiple statistics of a microwave link. The invention not only utilizes the time sequence change of signal attenuation, but also combines the statistical characteristics of signals on different time scales, takes the correlation degree as the criterion of self-adaptive selection statistics and effective links, can effectively mine available information, not only can obtain the weather wet and dry conditions on a single link, and can realize the sensitive monitoring of the weather wet and dry, weather and other regional distribution through the microwave link networking.
Drawings
FIG. 1 is a flow chart of an implementation of an adaptive wet-dry discrimination method based on multiple statistics of a microwave link;
fig. 2 is a diagram illustrating the implementation effect of an adaptive wet-dry distinguishing method based on multiple statistics of a microwave link.
Detailed Description
The present invention is further illustrated by the following description in conjunction with the accompanying drawings and the specific embodiments, it is to be understood that these examples are given solely for the purpose of illustration and are not intended as a definition of the limits of the invention, since various equivalent modifications will occur to those skilled in the art upon reading the present invention and fall within the limits of the appended claims.
In order to further improve the effect of microwave link rain measurement, a statistical means is adopted to analyze the correlation between the attenuation statistical parameters of the observation data of the microwave link and the rain, and the statistical parameters with high correlation are selected as the characteristic vector, taking the theory of a support vector machine as an example, as shown in fig. 1, the method comprises the following steps:
step 1: analyzing the correlation degree of the microwave link signal attenuation data and the dry and wet time:
step 1.1, calculating the attenuation mean value, the minimum value, the maximum value and other statistical parameters of the microwave link signal.
And step 1.2, researching and selecting a plurality of statistical parameters with high correlation degree with the dry and wet moments to form a feature vector supporting a vector machine classification algorithm.
Step 2: selecting an effective microwave link: due to the fact that the microwave link is susceptible to other factors, the correlation degree of rainfall and link attenuation data is reduced, the link attenuation data and the correlation of the dry and wet time are used as indexes, and the link with the high correlation degree is selected for dry and wet classification.
And step 3: taking the theory of a support vector machine as an example, the self-adaptive dry-wet distinguishing method based on the microwave link multi-statistic is established as follows:
step 3.1, forming a training data set x by using historical observation dataT,iAnd yT,i，xT,iIs a feature vector consisting of statistical parameters, yT,iDry and wet label values.
Step 3.2, constructing and solving an optimal solution of the convex quadratic programming problem:
Figure RE-GDA0002680548790000031
Figure RE-GDA0002680548790000032
solving the above equation to obtain alpha*Where K (-) is a kernel function, C>0 is a penalty parameter, α*Represents the optimal solution of convex quadratic problem, N represents the number of training set samples, alphaiRepresenting the Lagrangian multiplier, yT,iIndicating a dry-wet label, C indicating a penalty parameter, taking the value as>0。
Step 3.3, calculating to obtain a weight vector w of the classification function*：
Figure RE-GDA0002680548790000041
Step 3.4, calculating a classification function weight vector b:
Figure RE-GDA0002680548790000042
step 3.5, constructing a classification function:
Figure RE-GDA0002680548790000043
Wherein the content of the first and second substances,
Figure RE-GDA0002680548790000044
representing the optimal solution of the convex quadratic problem.
When f (x) is 1, the classification result indicates a wet time, and when f (x) is-1, the classification result indicates a dry time, and the classification result is shown in fig. 2.
The self-adaptive dry and wet distinguishing method can distinguish dry and wet moments by using the microwave link signal change, can effectively realize continuous monitoring of weather, and has important significance for further improving the precision of the microwave link rain measurement, improving the application benefit of the microwave link rain measurement method and the like.
Although the above description describes a complete embodiment including a link attenuation data and dry and wet time correlation analysis method, and a dry and wet identification method based on multiple statistics of microwave links, the above description is not limited to the above examples. Those skilled in the art should also appreciate that they can make various changes, modifications and substitutions within the spirit and scope of the present invention.

Claims (3)

1. A self-adaptive dry-wet distinguishing method based on microwave link multi-statistic is characterized by comprising the following steps:
step 1: analyzing the correlation degree of the microwave link signal attenuation data and the dry and wet time:
step 1.1, calculating statistical parameters of microwave link signals;
Step 1.2, selecting statistical parameters with high correlation degree with the dry and wet time to form a feature vector of a support vector machine classification algorithm;
step 2: selecting an effective microwave link: and selecting the link with high correlation degree to distinguish the dry state from the wet state by taking the correlation between the link attenuation data and the dry state as an index.
And step 3: establishing a self-adaptive dry-wet distinguishing method based on multiple statistics of a microwave link:
step 3.1, forming a training data set x by using historical observation dataT,iAnd yT,i，xT,iIs a feature vector consisting of statistical parameters, yT,iDry, wet label values;
step 3.2, constructing and solving an optimal solution of the convex quadratic programming problem:
Figure RE-FDA0002680548780000011
Figure RE-FDA0002680548780000012
solving the above equation to obtain alpha*Where K (. cndot.) is a kernel function, α*Represents the optimal solution of convex quadratic problem, N represents the number of training set samples, alphaiRepresenting the Lagrangian multiplier, yT,iIndicating a dry-wet label, C is a penalty parameter, and the value is>0；
Step 3.3, calculating to obtain a weight vector w of the classification function*：
Figure RE-FDA0002680548780000013
Step 3.4, calculating a classification function weight vector b:
Figure RE-FDA0002680548780000014
step 3.5, constructing a classification function:
Figure RE-FDA0002680548780000015
wherein the content of the first and second substances,
Figure RE-FDA0002680548780000016
representing the optimal solution of the convex quadratic problem.
2. The adaptive dry-wet distinguishing method based on the microwave link multi-statistic quantity according to claim 1, characterized in that: the statistical parameters comprise an attenuation mean value, a minimum value and a maximum value of the microwave link signal.
3. The adaptive dry-wet distinguishing method based on the microwave link multi-statistic quantity according to claim 1, characterized in that: when f (x) is 1, the classification result is the wet time, and when f (x) is-1, the classification result is the dry time.
CN202010236872.3A 2020-03-30 2020-03-30 Self-adaptive dry-wet distinguishing method based on multiple statistics of microwave link Active CN111860562B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010236872.3A CN111860562B (en) 2020-03-30 2020-03-30 Self-adaptive dry-wet distinguishing method based on multiple statistics of microwave link

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010236872.3A CN111860562B (en) 2020-03-30 2020-03-30 Self-adaptive dry-wet distinguishing method based on multiple statistics of microwave link

Publications (2)

Publication Number Publication Date
CN111860562A true CN111860562A (en) 2020-10-30
CN111860562B CN111860562B (en) 2022-04-12

Family

ID=72985896

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010236872.3A Active CN111860562B (en) 2020-03-30 2020-03-30 Self-adaptive dry-wet distinguishing method based on multiple statistics of microwave link

Country Status (1)

Country Link
CN (1) CN111860562B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112731567A (en) * 2021-01-11 2021-04-30 河海大学 Time-space collaborative dry-wet enhancement discrimination method for ultrahigh frequency microwave

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103926635A (en) * 2014-04-29 2014-07-16 中国人民解放军理工大学气象海洋学院 Method for monitoring rain area distribution by utilization of microwave link network
CN106547037A (en) * 2016-10-21 2017-03-29 中国人民解放军理工大学 The united raindrop size distribution inverting of double frequency dual-polarization microwave link and type of precipitation recognition methodss
US20170181672A1 (en) * 2015-12-28 2017-06-29 Medtronic Minimed, Inc. Sensor systems, devices, and methods for continuous glucose monitoring
CN107341449A (en) * 2017-06-14 2017-11-10 贵州中北斗科技有限公司 A kind of GMS Calculation of precipitation method based on cloud mass changing features
US20170371074A1 (en) * 2016-06-24 2017-12-28 Climacell Inc. Real-Time Precipitation Forecasting System
CN109581546A (en) * 2018-10-30 2019-04-05 中国人民解放军国防科技大学 Rainfall type identification method based on microwave link attenuation and polarization information
CN110059713A (en) * 2019-03-07 2019-07-26 中国人民解放军国防科技大学 Precipitation type identification method based on precipitation particle multi-feature parameters
US20190339416A1 (en) * 2017-11-03 2019-11-07 Climacell Inc. Real-time data pipeline techniques for improving a fast weather forecasting system

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103926635A (en) * 2014-04-29 2014-07-16 中国人民解放军理工大学气象海洋学院 Method for monitoring rain area distribution by utilization of microwave link network
US20170181672A1 (en) * 2015-12-28 2017-06-29 Medtronic Minimed, Inc. Sensor systems, devices, and methods for continuous glucose monitoring
US20170371074A1 (en) * 2016-06-24 2017-12-28 Climacell Inc. Real-Time Precipitation Forecasting System
CN106547037A (en) * 2016-10-21 2017-03-29 中国人民解放军理工大学 The united raindrop size distribution inverting of double frequency dual-polarization microwave link and type of precipitation recognition methodss
CN107341449A (en) * 2017-06-14 2017-11-10 贵州中北斗科技有限公司 A kind of GMS Calculation of precipitation method based on cloud mass changing features
US20190339416A1 (en) * 2017-11-03 2019-11-07 Climacell Inc. Real-time data pipeline techniques for improving a fast weather forecasting system
CN109581546A (en) * 2018-10-30 2019-04-05 中国人民解放军国防科技大学 Rainfall type identification method based on microwave link attenuation and polarization information
CN110059713A (en) * 2019-03-07 2019-07-26 中国人民解放军国防科技大学 Precipitation type identification method based on precipitation particle multi-feature parameters

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
KUN SONG 等: "Rainfall estimation using a microwave link based on an improved rain-induced attenuation model", 《REMOTE SENSING LETTERS》 *
刘西川: "微波链路降水测量技术及应用研究进展综述", 《装备环境工程》 *
宋堃 等: "基于支持向量机的微波链路雨强反演方法研究", 《第33届中国气象学会年会 S12 大气物理学与大气环境》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112731567A (en) * 2021-01-11 2021-04-30 河海大学 Time-space collaborative dry-wet enhancement discrimination method for ultrahigh frequency microwave
CN112731567B (en) * 2021-01-11 2021-09-21 河海大学 Time-space collaborative dry-wet enhancement discrimination method for ultrahigh frequency microwave

Also Published As

Publication number Publication date
CN111860562B (en) 2022-04-12

Similar Documents

Publication Publication Date Title
CN109581546B (en) Rainfall type identification method based on microwave link attenuation and polarization information
CN108629452A (en) A kind of Weather Risk decision-making technique based on multi-mode multi-parameter DATA PROCESSING IN ENSEMBLE PREDICTION SYSTEM
CN109547133A (en) A kind of SVM high-efficiency frequency spectrum cognitive method decomposing sample covariance matrix based on Cholesky
CN111913156A (en) Radar radiation source individual identification method based on deep learning model and feature combination
CN107330898B (en) Quantitative marking calculation method and system for vegetation vertical zone
CN109299698B (en) Wireless channel scene recognition method based on support vector machine
CN108073902A (en) Video summary method, apparatus and terminal device based on deep learning
CN113177360B (en) Rain intensity self-adaptive estimation system and method based on clustering rain attenuation relation
CN110346800A (en) A kind of thunderstorm recognition methods based on dual-polarization weather radar body total number evidence
CN110059713A (en) Precipitation type identification method based on precipitation particle multi-feature parameters
CN111860562B (en) Self-adaptive dry-wet distinguishing method based on multiple statistics of microwave link
CN115659284B (en) Big data fusion platform
CN110570462A (en) flood inundation range automatic extraction method based on polarized radar remote sensing image
CN111901028B (en) Human body behavior identification method based on CSI (channel State information) on multiple antennas
CN111461923A (en) Electricity stealing monitoring system and method based on deep convolutional neural network
CN110705619A (en) Fog concentration grade judging method and device
CN108229507A (en) Data classification method and device
CN116707675B (en) Method and device for detecting radio signal and method and device for detecting abnormality of radio signal
CN116503912B (en) Security check early warning method based on electronic graph bag
Li et al. TF 2 AN: A temporal-frequency fusion attention network for spectrum energy level prediction
CN112749699A (en) 5G network communication method and system for water meter
CN113191224A (en) Unmanned aerial vehicle signal extraction and identification method and system
CN110907015B (en) Liquid level monitoring method based on RFID (radio frequency identification) in indoor environment
CN113098640B (en) Frequency spectrum anomaly detection method based on channel occupancy prediction
CN112101486B (en) Chip screening method and device, electronic equipment and readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant