Patent · US Active

Numerical controller with learned pressure estimation

US10802476B2 · kind B2 · utility

0Cited by
3References
12Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 23, 2018
Grant dateOct 13, 2020
Priority date—
Expiry dateJul 27, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG05B2219/42155
  • WIPO fieldControl
  • WIPO sectorInstruments

Abstract

Provided is a numerical controller capable of easily controlling a pressure without a pressure sensor. The numerical controller estimates a pressure based on at least one of a command value and a feedback value. A machine learning device for learning the pressure corresponding to the at least one of the command value and the feedback value is included. The machine learning device includes a state observation unit for observing the at least one of the command value and the feedback value as a state variable, a label data acquisition unit for acquiring label data indicating the pressure, and a learning unit for associating and learning the state variable with the label data.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.