http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111665718-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G05B13-04 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G05B13-04 |
filingDate | 2020-06-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2022-05-10-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2022-05-10-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-111665718-B |
titleOfInvention | Diagonal recurrent neural network control method based on Q learning algorithm |
abstract | The invention designs a Diagonal Recurrent Neural Network (DRNN) control method (Q-DRNN) based on a Q learning algorithm, wherein the Q-DRNN organically combines the strong search capability of Q learning with the advantages of a self-carrying recurrent ring structure, dynamic mapping capability, adaptation time variation and the like of the DRNN and is used for improving the working stability of a brushless direct current motor (BLDCM). In Q-DRNN, DRNN iterates the output variables through the unique recursion loops in the hidden layer, and optimizes the key weights of the output variables to accelerate the iteration speed. Meanwhile, the improved Q learning is introduced to correct the weight parameter factor of the DRNN, so that the DRNN has self-learning and online correction capabilities, the anti-interference capability of the system is enhanced, the robustness is enhanced, and the brushless direct current motor achieves a better control effect. |
priorityDate | 2020-06-05-04:00^^<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/CID28718 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419513094 |
Total number of triples: 12.