Title:
MACHINE LEARNING DEVICE, DATA PROCESSING SYSTEM, INFERENCE DEVICE, AND MACHINE LEARNING METHOD
Document Type and Number:
WIPO Patent Application WO/2021/192984
Kind Code:
A1
Abstract:
[Problem] To provide a machine learning device, etc. with which an abnormalities and signs of abnormalities in a fluid pressure-driven valve can be accurately ascertained without depending on the experience of an operator or the like. [Solution] A machine learning device (200) is utilized in an electromagnetic valve device comprising: a drive device (12); and an electromagnetic valve (1) including a spool part (2) that switches a flow path of a drive fluid (A) which flows to the drive device (12), and a solenoid part (3) that displaces the spool part (2) depending on an energization state. The machine learning device comprises: a learning data set storage unit (202) that stores a plurality of learning data sets comprising input data including time-series data of an electromagnetic valve input-side pressure of the drive fluid (A), time-series data of an electromagnetic valve output-side pressure of the drive fluid (A), and time-series data of a supply voltage of the solenoid part in a certain period, and output data comprising diagnostic information of the spool part (2) associated with the input data; a learning unit (203) into which the plurality of learning data sets are input, and which learns a learning model that infers a correlation between the input data and the output data; and a learned model storage unit (204) that stores a learned model.
More Like This:
| JPH06109005 | VALVE DRIVING CYLINDER |
Inventors:
AOYAMA FUMIAKI (JP)
Application Number:
PCT/JP2021/009121
Publication Date:
September 30, 2021
Filing Date:
March 09, 2021
Export Citation:
Assignee:
KANEKO SANGYO CO LTD (JP)
International Classes:
F16K31/163; F16K37/00; G05B23/02; G16Y10/25; G16Y40/10
Domestic Patent References:
| WO2019235599A1 | 2019-12-12 |
Foreign References:
| JPH0861551A | 1996-03-08 | |||
| JPH0413935A | 1992-01-17 |
Attorney, Agent or Firm:
AOYAMA, Jun et al. (JP)
Download PDF: