http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110400007-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/G06Q10-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06Q10-06393 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-044 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06Q10-06 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06Q10-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
filingDate | 2019-07-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0df7b4436b00a7bbec546a4cc8fe2b56 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ee75568a4041aad96e8ea128bdebdcef |
publicationDate | 2019-11-01-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-110400007-A |
titleOfInvention | Prediction method of molten iron quality based on improved gated recurrent neural network |
abstract | The invention discloses a molten iron quality prediction method based on an improved gated cyclic neural network. Due to its unique internal unit, GRU is particularly suitable for processing time series data with time-delay effect, but the existing GRU has a complex structure and a large amount of calculation, which is not suitable for the requirements of real-time, reliability and accuracy in the process industry. The present invention provides a gated recurrent neural network with a disposal gate unit, which is used for molten iron quality prediction. By combining the update gate and reset gate in the traditional GRU into a single disposition gate, compared with the traditional recurrent neural network (RNN), long short-term memory neural network (LSTM-RNN) and gated recurrent neural network (GRU-RNN), The model complexity is effectively reduced, the calculation amount is reduced, and the prediction accuracy is improved, and the online real-time prediction of the molten iron quality can be realized. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111103420-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113223634-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111103420-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111950697-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113325811-A |
priorityDate | 2019-07-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 29.