http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113569473-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_d6a6f422b091ba12ea61d4adbf1b0e8e |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-044 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/F17D5-005 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F30-27 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/F17D1-02 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F30-27 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/F17D5-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/F17D1-02 |
filingDate | 2021-07-19-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_5c0536a0313177d030e193b051fd8017 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_653b6f982c6fd7b2b60ce15ea6859894 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_1b50d3d25780239e67c17b76b4d61e76 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_cf3b644fdfcd3b90753df3ae696410f8 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9c754c5b200ff0b0983d06ecc3902c1d |
publicationDate | 2021-10-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-113569473-A |
titleOfInvention | Long-term prediction method of oxygen in air separation pipeline network based on polynomial feature LSTM granularity calculation |
abstract | The invention discloses a long-term oxygen prediction method based on polynomial feature LSTM granularity calculation for air separation pipe network. The method firstly divides the oxygen demand time series data by adaptive granularity according to concave-convexity and monotonicity, and then divides each data particle to form an adaptive granularity. Granular feature description based on quadratic polynomial. In the prediction stage, long-term prediction of each granularity feature is carried out through the long-term and short-term memory network, and then the final long-term prediction result of oxygen demand is obtained through inverse granularity, which assists and guides the on-site oxygen scheduling work. The method can consider the long-term and short-term dependence of oxygen demand data through a long-short-term memory network and obtain long-term prediction of oxygen demand by predicting granularity characteristics. Compared with the existing method, the present invention has better accuracy and can be implemented online, and can provide guidance to dispatchers in real time. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115331415-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114595879-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114595879-A |
priorityDate | 2021-07-19-04:00^^<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/compound/CID977 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419523291 |
Total number of triples: 28.