Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_d6a6f422b091ba12ea61d4adbf1b0e8e |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-044 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01R31-388 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01R31-367 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01R31-388 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01R31-367 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 |
filingDate |
2019-11-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_43f12893799d57db76ceaad5b7b176e4 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_d9434b08fa08cca5d16e614043cf2059 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_c93667ecac5a2cee2d4d8d2234a3a917 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a3e97885df87ce394323840c5bce76ab |
publicationDate |
2020-04-14-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-111007399-A |
titleOfInvention |
State-of-charge prediction method of lithium battery based on improved generative adversarial network |
abstract |
The invention provides a method for predicting the state of charge of a lithium battery based on an improved generative adversarial network, comprising the following steps: collecting modal parameters of the lithium battery and the real state of charge SOC in the lithium battery sample; using a regression model R to estimate the generation model G outputs the lower bound value of the mutual information between G(z,c) and the condition variable c; makes the generative model G and the discriminant model D confront each other to achieve Nash equilibrium; use the generative model G to generate samples and add them to the regression model The training set used by R is trained; the generator model G, the discriminant model D and the regression model R are alternately trained so that each model tends to converge. The invention uses the generative model to expand the training set conforming to the original distribution, and simultaneously uses two activation functions of random correction linear unit RReLU and exponential linear unit Exponential Linear Units (ELU) in the improved generative confrontation network to obtain stronger model expressiveness, and more Good to learn the nonlinear characteristics of lithium batteries. |
isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115542173-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113900033-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113328466-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113328466-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113900033-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111832221-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111832221-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114236410-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113884905-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113884905-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112287979-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112287979-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-116087814-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112269134-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112269134-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112668239-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112668239-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114545255-A |
priorityDate |
2019-11-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |