Lightweight distributed optical fiber sensing event identification method and system
The invention belongs to the related technical field of optical fiber sensing event image recognition, and provides a distributed optical fiber sensing event recognition method and system based on lightweight, and the method comprises the steps: converting distributed sensor event time sequence sign...
Gespeichert in:
Hauptverfasser: | , , , , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | WANG CHANG ZHANG FAXIANG WANG CHUNXIAO JIANG SHAODONG DONG HUOMIN ZHANG HONGYU WANG JINWEI YANG ZHENGUO |
description | The invention belongs to the related technical field of optical fiber sensing event image recognition, and provides a distributed optical fiber sensing event recognition method and system based on lightweight, and the method comprises the steps: converting distributed sensor event time sequence signal data into a Markov transition field two-dimensional image based on a Markov transition field; pre-training an established teacher network model by using the obtained image; performing first-order knowledge distillation training of a middle feature layer on the established student network model by using a pre-trained teacher network model; performing second-order knowledge distillation training on the output feature layer of the student network model by using a pre-trained teacher network model and the student network model subjected to the first-order knowledge distillation to obtain a trained student network model; identification is carried out through the trained student network model, the identification preci |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116091897A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116091897A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116091897A3</originalsourceid><addsrcrecordid>eNqNirEKwkAQBa-xEPUf1g8QPAQ1pQTFQqzSh0vuJVlI7o7sqvj3RvADbGaKmbkpbtx2-sKX5Fl05Oqh8BSTcu16arjCSIIgHFrCE0GJ_URupq4cAw3QLnpywZO8RTEszaxxvWD188KsL-civ26QYglJrkaAlvnd2v02s8fscNr983wAFZQ5wg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Lightweight distributed optical fiber sensing event identification method and system</title><source>esp@cenet</source><creator>WANG CHANG ; ZHANG FAXIANG ; WANG CHUNXIAO ; JIANG SHAODONG ; DONG HUOMIN ; ZHANG HONGYU ; WANG JINWEI ; YANG ZHENGUO</creator><creatorcontrib>WANG CHANG ; ZHANG FAXIANG ; WANG CHUNXIAO ; JIANG SHAODONG ; DONG HUOMIN ; ZHANG HONGYU ; WANG JINWEI ; YANG ZHENGUO</creatorcontrib><description>The invention belongs to the related technical field of optical fiber sensing event image recognition, and provides a distributed optical fiber sensing event recognition method and system based on lightweight, and the method comprises the steps: converting distributed sensor event time sequence signal data into a Markov transition field two-dimensional image based on a Markov transition field; pre-training an established teacher network model by using the obtained image; performing first-order knowledge distillation training of a middle feature layer on the established student network model by using a pre-trained teacher network model; performing second-order knowledge distillation training on the output feature layer of the student network model by using a pre-trained teacher network model and the student network model subjected to the first-order knowledge distillation to obtain a trained student network model; identification is carried out through the trained student network model, the identification preci</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2023</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230509&DB=EPODOC&CC=CN&NR=116091897A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25562,76317</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230509&DB=EPODOC&CC=CN&NR=116091897A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WANG CHANG</creatorcontrib><creatorcontrib>ZHANG FAXIANG</creatorcontrib><creatorcontrib>WANG CHUNXIAO</creatorcontrib><creatorcontrib>JIANG SHAODONG</creatorcontrib><creatorcontrib>DONG HUOMIN</creatorcontrib><creatorcontrib>ZHANG HONGYU</creatorcontrib><creatorcontrib>WANG JINWEI</creatorcontrib><creatorcontrib>YANG ZHENGUO</creatorcontrib><title>Lightweight distributed optical fiber sensing event identification method and system</title><description>The invention belongs to the related technical field of optical fiber sensing event image recognition, and provides a distributed optical fiber sensing event recognition method and system based on lightweight, and the method comprises the steps: converting distributed sensor event time sequence signal data into a Markov transition field two-dimensional image based on a Markov transition field; pre-training an established teacher network model by using the obtained image; performing first-order knowledge distillation training of a middle feature layer on the established student network model by using a pre-trained teacher network model; performing second-order knowledge distillation training on the output feature layer of the student network model by using a pre-trained teacher network model and the student network model subjected to the first-order knowledge distillation to obtain a trained student network model; identification is carried out through the trained student network model, the identification preci</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNirEKwkAQBa-xEPUf1g8QPAQ1pQTFQqzSh0vuJVlI7o7sqvj3RvADbGaKmbkpbtx2-sKX5Fl05Oqh8BSTcu16arjCSIIgHFrCE0GJ_URupq4cAw3QLnpywZO8RTEszaxxvWD188KsL-civ26QYglJrkaAlvnd2v02s8fscNr983wAFZQ5wg</recordid><startdate>20230509</startdate><enddate>20230509</enddate><creator>WANG CHANG</creator><creator>ZHANG FAXIANG</creator><creator>WANG CHUNXIAO</creator><creator>JIANG SHAODONG</creator><creator>DONG HUOMIN</creator><creator>ZHANG HONGYU</creator><creator>WANG JINWEI</creator><creator>YANG ZHENGUO</creator><scope>EVB</scope></search><sort><creationdate>20230509</creationdate><title>Lightweight distributed optical fiber sensing event identification method and system</title><author>WANG CHANG ; ZHANG FAXIANG ; WANG CHUNXIAO ; JIANG SHAODONG ; DONG HUOMIN ; ZHANG HONGYU ; WANG JINWEI ; YANG ZHENGUO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116091897A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>WANG CHANG</creatorcontrib><creatorcontrib>ZHANG FAXIANG</creatorcontrib><creatorcontrib>WANG CHUNXIAO</creatorcontrib><creatorcontrib>JIANG SHAODONG</creatorcontrib><creatorcontrib>DONG HUOMIN</creatorcontrib><creatorcontrib>ZHANG HONGYU</creatorcontrib><creatorcontrib>WANG JINWEI</creatorcontrib><creatorcontrib>YANG ZHENGUO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WANG CHANG</au><au>ZHANG FAXIANG</au><au>WANG CHUNXIAO</au><au>JIANG SHAODONG</au><au>DONG HUOMIN</au><au>ZHANG HONGYU</au><au>WANG JINWEI</au><au>YANG ZHENGUO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Lightweight distributed optical fiber sensing event identification method and system</title><date>2023-05-09</date><risdate>2023</risdate><abstract>The invention belongs to the related technical field of optical fiber sensing event image recognition, and provides a distributed optical fiber sensing event recognition method and system based on lightweight, and the method comprises the steps: converting distributed sensor event time sequence signal data into a Markov transition field two-dimensional image based on a Markov transition field; pre-training an established teacher network model by using the obtained image; performing first-order knowledge distillation training of a middle feature layer on the established student network model by using a pre-trained teacher network model; performing second-order knowledge distillation training on the output feature layer of the student network model by using a pre-trained teacher network model and the student network model subjected to the first-order knowledge distillation to obtain a trained student network model; identification is carried out through the trained student network model, the identification preci</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | chi ; eng |
recordid | cdi_epo_espacenet_CN116091897A |
source | esp@cenet |
subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
title | Lightweight distributed optical fiber sensing event identification method and system |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T15%3A17%3A00IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=WANG%20CHANG&rft.date=2023-05-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116091897A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |