Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020111317 - MACHINE LEARNING TECHNIQUE-BASED ALGORITHM AND METHOD FOR DETECTING ERRONEOUS DATA OF MACHINE

Publication Number WO/2020/111317
Publication Date 04.06.2020
International Application No. PCT/KR2018/014895
International Filing Date 29.11.2018
IPC
G05D 1/02 2006.01
GPHYSICS
05CONTROLLING; REGULATING
DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
1Control of position, course, altitude, or attitude of land, water, air, or space vehicles, e.g. automatic pilot
02Control of position or course in two dimensions
G06K 9/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
B60W 40/06 2006.01
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
40Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit
02related to ambient conditions
06Road conditions
B60W 30/18 2006.01
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
30Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
18Propelling the vehicle
CPC
B60W 30/18
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
30Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units ; , or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
18Propelling the vehicle
B60W 40/06
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
40Estimation or calculation of ; non-directly measurable; driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, ; e.g. by using mathematical models
02related to ambient conditions
06Road conditions
G05D 1/02
GPHYSICS
05CONTROLLING; REGULATING
DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
1Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
02Control of position or course in two dimensions
G06K 9/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
Applicants
  • 울랄라랩 주식회사 ULALA LAB. INC [KR]/[KR]
Inventors
  • 강학주 KANG, Hak Ju
Agents
  • 특허법인 엠에이피에스 MAPS INTELLECTUAL PROPERTY LAW FIRM
Priority Data
Publication Language Korean (KO)
Filing Language Korean (KO)
Designated States
Title
(EN) MACHINE LEARNING TECHNIQUE-BASED ALGORITHM AND METHOD FOR DETECTING ERRONEOUS DATA OF MACHINE
(FR) ALGORITHME BASÉ SUR UNE TECHNIQUE D'APPRENTISSAGE AUTOMATIQUE ET PROCÉDÉ DE DÉTECTION DE DONNÉES ERRONÉES DE MACHINE
(KO) 기계학습 기법에 기반한 기계의 오류 데이터를 검출하기 위한 알고리즘 및 방법
Abstract
(EN)
The present invention may automatically detect time-series threshold data in a server on the basis of a machine learning technique, and on this basis, can compare operation data in the entire time domain. Accordingly, there is no need for a worker to manually input threshold data. In addition, the present invention may precisely detect faults in machinery or product defects that could not be discovered when setting thresholds (absolute value) in the past.
(FR)
La présente invention peut détecter automatiquement des données de seuil chronologiques dans un serveur sur la base d'une technique d'apprentissage automatique, et sur cette base, peut comparer des données de fonctionnement dans l'ensemble du domaine temporel. En conséquence, un travailleur n'a pas besoin de saisir manuellement des données de seuil. De plus, la présente invention peut détecter précisément des défauts dans des machines ou des défauts de produit qui pourraient ne pas être découverts lors de la définition de seuils (valeur absolue) dans le passé.
(KO)
본 발명은 시계열적인 임계치 데이터를 서버에서 머신러닝 기법 기반으로 자동으로 검출해내고, 이를 기반으로 모든 시간 영역에서 동작데이터를 비교할 수 있다. 그에 따라, 작업자가 수기로 임계치 데이터를 입력할 필요가 없다. 또한, 본 발명은 종래의 임계치(절대값) 설정시 발견할 수 없었던 기계의 결함이나 제품 불량을 정밀하게 검출할 수 있다.
Latest bibliographic data on file with the International Bureau