http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114896832-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_ae2be58a477cef66248d0dc28cb0ea82 |
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F2119-08 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F30-23 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F30-27 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-23 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06Q10-04 |
| classificationIPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F119-08 |
| classificationIPCInventive | 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/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F30-27 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F30-23 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06Q10-04 |
| filingDate | 2022-03-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_568f3ee8eb95e204a8b537157f5db4a0 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_4b7ac3277e2097d3834db4ffe4b2c8d1 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_410a4ea6e65526ea48a2606cca88dfa9 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_13bbdc615dbe8dfa42971ff365a96ee1 |
| publicationDate | 2022-08-12-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-114896832-A |
| titleOfInvention | Conv1D-MGU thermal error prediction model and thermal error control system based on physics-data-edge-cloud architecture |
| abstract | The invention discloses a Conv1D-MGU thermal error prediction model, comprising an input layer, an MGU layer, a fully connected layer and an output layer arranged in sequence; a residual block is arranged between the input layer and the MGU layer, and the The residual block includes a main path and a shortcut branch, one end of the main path and the shortcut branch is respectively connected with the input layer, and the other end is connected with the accumulation layer; A one-dimensional convolution pooling unit and a one-dimensional convolution layer II between the accumulation layers, the one-dimensional convolution pooling unit is set to at least one in series, and the one-dimensional convolution pooling unit includes one-dimensional convolution pooling units arranged in sequence A convolution layer I, a one-dimensional pooling layer and an activation function layer I; an activation function layer II is arranged between the accumulation layer and the MGU layer, and an expansion function layer II is arranged between the activation function layer II and the MGU layer. leveling; the shortcut branch is provided with downsampling. The invention also discloses a thermal error control system based on the physical-data-edge-cloud architecture. |
| priorityDate | 2022-03-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 30.