http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-2020519909-A
Outgoing Links
Predicate | Object |
---|---|
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24155 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24323 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24147 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01M3-24 |
filingDate | 2018-04-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2020-07-02-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | JP-2020519909-A |
titleOfInvention | Water leak detection method for water pipes |
abstract | The present invention includes a step S1 of obtaining sample sound wave data labeled leak/non-leak, generating a feature training base based on the sample data, and training the feature training base using an integrated model to obtain a leak classifier. Step S2 of generating a feature identification base based on the detection data, Step S3 of generating a feature identification base based on the detection data, and arranging the feature identification base in a water leak classifier for measurement to generate a judgment result of every leaked/non-leaked water Classifying the judgment results one by one according to the collection point of data, creating a time tag and a place tag for the identification sequence, the one by one judgment result, generating an identification rule tree by combining the time tag and the place tag, Disclosed is a water pipe leakage detection method including a step S5 of voting according to an identification rule tree to generate a final judgment result including leakage or non-leakage and probabilities corresponding thereto. According to the present invention, pipe sound wave data can be analyzed in real time, the conventional data analysis method can be simplified, the accuracy of data analysis can be improved, the work efficiency is high, and the accuracy can be continuously improved through self-learning. it can. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2023191307-A1 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-102454925-B1 |
priorityDate | 2017-07-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Predicate | Subject |
---|---|
isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419512635 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID962 |
Total number of triples: 18.