http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113311364-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01R31-54 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F17-16 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01R31-343 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01R31-54 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01R31-34 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F17-16 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 |
filingDate | 2021-05-07-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2022-11-01-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2022-11-01-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-113311364-B |
titleOfInvention | Open-circuit fault diagnosis method of permanent magnet synchronous motor inverter based on multi-core SVM |
abstract | The invention discloses a multi-core SVM-based permanent magnet synchronous motor inverter open-circuit fault diagnosis method. The method includes the following steps: collecting inverter open-circuit and normal three-phase current signals through a current sensor; based on variational modal decomposition , decompose and reconstruct the collected three-phase current signals, and construct a sample data set; arbitrarily select the combined kernel function; construct a mathematical optimization problem with the largest sample data classification interval through the EasyMKL multi-kernel learning algorithm and solve the weight coefficient η; set the weight coefficient threshold p , trim the kernel function whose weight coefficient η is less than the threshold p, and output the combined kernel function after trimming; according to the combined kernel function and the SVM classifier, the purpose of diagnosing the open circuit fault of the inverter IGBT tube is realized. The invention introduces a multi-core learning algorithm on the basis of the traditional SVM classification method, and has higher fault diagnosis accuracy than the traditional SVM method. |
priorityDate | 2021-05-07-04:00^^<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/substance/SID419559532 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID24404 |
Total number of triples: 18.