http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-H06348873-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_80787665b837ed3eb503bbcd27c0043a |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N99-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06G7-60 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F15-18 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G05B13-02 |
filingDate | 1993-06-02-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b34443cd16f7148cd86c0b845e45a952 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_74a99e90f7007a52fe0a4d314faea089 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_19ad41b6cfd2fe4e7478615e5910e31c http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_11eb95ac1d1153ad8a0c0f7d3c1d7c5f http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_983fbf9dc2c04749c28642dca27c30ed http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_781c56c891d5574e4a472a84da49f4c8 |
publicationDate | 1994-12-22-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | JP-H06348873-A |
titleOfInvention | Support system using neural network, plant operation support system using it, automatic additional learning method of neural network |
abstract | (57) [Abstract] [Purpose] To perform automatic additional learning of a neural network in a plant operation support system with low load on hardware and high efficiency. [Structure] A plant operation support system 200 that displays quantitative guidance via a CRT 190 and provides operation support to an operator who manages a plant system for a water purification process is a neural network as means for calculating a predicted value for support. Neuro system 230 using network The neural network corresponding to the input condition is reconstructed by the automatic additional learning method. The cycle for the automatic additional learning of this neural network is the learning cycle and learning judgment that minimize the average recall error by recalling by the combination of the learning cycle and the learning judgment history period (number of days) when constructing a new neural network. By finding a combination with the history period (number of days), it is set in conformity with the conditions and changes at the same time. |
priorityDate | 1993-06-02-04:00^^<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/SID419512635 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID962 |
Total number of triples: 20.