Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
MACHINED-SURFACE DETERMINATION DEVICE, MACHINED-SURFACE DETERMINATION PROGRAM, MACHINED-SURFACE DETERMINATION METHOD, AND MACHINING SYSTEM
Document Type and Number:
WIPO Patent Application WO/2022/085253
Kind Code:
A1
Abstract:
A machined-surface determination device (7) is provided with: an image acquisition unit (70) that acquires a determination image (42) including a prescribed determination image region in which a machined surface of a determination subject is captured; an inference unit (71) in which a plurality of small images (43) generated from the determination image (42) by dividing the determination image region into small image regions are individually input to a learning model (2) that has learned, through machine learning, correlations between training images including training image regions corresponding to the small image regions and classification results in which the conditions of machined surfaces included in the training images are classified into one of a plurality of machined conditions, whereby classification results for the plurality of small images (43) are inferred individually for the small images; a classification-result processing unit (73) that obtains a processing result by processing the classification results for the plurality of small images (43), inferred individually for the small images; and a determination unit (75) that determines the condition of the machined surface on the basis of the processing result.

Inventors:
UCHIMURA TOMOYUKI (JP)
SAKAI TOMOYA (JP)
ORITA KENTARO (JP)
Application Number:
PCT/JP2021/026260
Publication Date:
April 28, 2022
Filing Date:
July 13, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
EBARA CORP (JP)
International Classes:
G01B11/30; G01N21/88; G06N3/08; G06N20/00; G06T7/00
Domestic Patent References:
WO2018235266A12018-12-27
Foreign References:
JP2019056668A2019-04-11
JP2019211415A2019-12-12
CN109632817A2019-04-16
Attorney, Agent or Firm:
HIROSAWA, Tetsuya et al. (JP)
Download PDF: