http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110121682-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_5d7576285d411d00c697e07270d2814a |
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G05B2219-24033 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G05B23-0221 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G05B23-0205 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N5-01 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N5-022 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G05B23-0283 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N5-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G05B23-02 |
filingDate | 2017-09-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a8ee686ffdfae35c12e0410801fc5b05 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_08cdd231c0028f79becdaab8f901f9f6 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_524ac2091ad27c8eb14c583b0c8a4921 |
publicationDate | 2019-08-13-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-110121682-A |
titleOfInvention | Method and system for finding omen subsequences in a time series |
abstract | A system and method for determining patterns in time series data representing the operation of a machine. The memory stores and provides a set of training data examples generated by the machine's sensors, wherein each training data example represents the operation of the machine during a period culminating in a machine failure. The processor is configured to iteratively divide each training data instance into normal regions and abnormal regions, determine prediction patterns that are absent from the normal regions and occur only once in each abnormal region, and determine the length of the abnormal regions. Predictive patterns are output via an output interface in communication with the processor or stored in memory, where the predictive patterns are predictive estimates of impending failures and help manage the machine. |
priorityDate | 2016-12-12-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 22.