Title:
MACHINE LEARNING DEVICE, DATA PROCESSING SYSTEM, INFERENCE DEVICE, AND MACHINE LEARNING METHOD
Document Type and Number:
WIPO Patent Application WO/2021/220767
Kind Code:
A1
Abstract:
[Problem] To provide a machine learning device which makes it possible to accurately recognize an abnormality and a sign of abnormality in an electromagnetic valve device without depending on the experience of a worker, etc. [Solution] This machine learning device (200) is applied to an electromagnetic valve device including a driving device (12) which includes a cylinder and a piston, and an electromagnetic valve (1) which controls the supply and discharge of a driving fluid (A) to and from the driving device (12), and comprises: a training data set storage unit (202) which stores a plurality of training data sets composed of input data including the temperature and humidity in the cylinder and output data that is composed of diagnostic information about the driving device (12) and corresponds to the input data; a training unit (203) which receives as inputs the plurality of training data sets and trains a training model that infers a correlation between the input data and the output data; and a trained model storage unit (204) which stores the trained model.
Inventors:
AOYAMA FUMIAKI (JP)
Application Number:
PCT/JP2021/014972
Publication Date:
November 04, 2021
Filing Date:
April 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: