http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113223634-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/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16C20-70 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16C20-30 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16C20-30 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16C20-70 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
| filingDate | 2021-03-22-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_daf3d1d1b9344803804ed645cea661ab http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_020b4abffbf39d7fa791abb205c43a28 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ee75568a4041aad96e8ea128bdebdcef |
| publicationDate | 2021-08-06-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-113223634-A |
| titleOfInvention | Prediction method of silicon content in blast furnace hot metal based on two-dimensional self-attention enhanced GRU model |
| abstract | The invention discloses a method for predicting silicon content in blast furnace molten iron based on a two-dimensional self-attention enhanced GRU model, belonging to the fields of industrial process monitoring, modeling and simulation. By obtaining effective information from the real blast furnace production data, a model is established to achieve advance prediction of the silicon content in molten iron and guide subsequent production operations. Considering that the influence of each parameter variable on the silicon content of molten iron in the blast furnace production process is different and changes dynamically with time, it is proposed to increase the self-attention in the feature dimension of the GRU model to obtain the dynamic weight of each parameter variable; at the same time, considering the system dynamics and large In order to solve the problem of time delay, a time dimension self-attention mechanism based on causal convolution is proposed to realize enhanced perception of local dynamic characteristics of blast furnace operating parameters, and soft benchmarking between operating parameters and process indicators; the method of the present invention has large time delay and strong dynamic performance. The blast furnace system has a good fitting effect and can accurately predict the silicon content of the blast furnace molten iron. |
| priorityDate | 2021-03-22-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 28.