Machine learning device, control system, and machine learning method

Patent metadata

Field	Value
Publication number	US-11029650-B2
Application number	US-201916510027-A
Country	US
Kind code	B2
Filing date	Jul 12, 2019
Priority date	Aug 30, 2018
Publication date	Jun 8, 2021
Grant date	Jun 8, 2021

Abstract

Setting of parameters that determine filter characteristics is facilitated. Machine learning of optimizing the coefficients of a filter provided in a motor control device that controls rotation of a motor for a machine tool, a robot, or an industrial machine is performed on the basis of measurement information of an external measuring instrument provided outside the motor control device and a control command input to the motor control device.

First claim

What is claimed is:

1. A machine learning device that performs machine learning of optimizing coefficients of a filter provided outside a servo control unit and provided in a motor control device that controls the rotation of a motor on the basis of measurement information of an external measuring instrument provided outside the motor control device and a control command input to the motor control device, the machine learning device comprising:
a state information acquisition unit that acquires state information including the measurement information, the control command, and the coefficients of the filter;
an action information output unit that outputs action information including adjustment information of the coefficients included in the state information to the filter;
a reward output unit that outputs a reward value for reinforcement learning using a value function based on a difference between the measurement information and the control command; and
a value function updating unit that updates an action value function on the basis of the reward value output by the reward output unit, the state information, and the action information.

2. The machine learning device according to claim 1 , wherein
the measurement information of the external measuring instrument includes at least one of a position, a velocity, and an acceleration.

3. The machine learning device according to claim 1 , wherein
the motor control device includes at least one of a position feedback loop and a velocity feedback loop, and the filter is provided outside the position feedback loop or the velocity feedback loop.

4. The machine learning device according to claim 1 , wherein
the motor control device has a feedback loop, and the measurement information of the external measuring instrument is not used for feedback control of the feedback loop.

5. The machine learning device according to claim 1 , wherein
the external measuring instrument is detached after adjustment of the filter by machine learning.

6. The machine learning device according to claim 1 , further comprising:
an optimization action information output unit that outputs adjustment information of the coefficients on the basis of the value function updated by the value function updating unit.

7. A control system comprising:
a motor control device that includes the machine learning device according to claim 1 , a motor, and a filter and controls the rotation of the motor; and
an external measuring instrument provided outside the motor control device.

8. A machine learning method of a machine learning device that performs machine learning of optimizing coefficients of a filter provided outside a servo control unit and provided in a motor control device that controls the rotation of a motor on the basis of measurement information of an external measuring instrument provided outside the motor control device and a control command input to the motor control device, the machine learning method comprising:
acquiring state information including the measurement information, the control command, and the coefficients of the filter;
outputting action information including adjustment information of the coefficients included in the state information to the filter;
outputting a reward value for reinforcement learning using a value function based on a difference between the measurement information and the control command; and
updating an action value function on the basis of the reward value, the state information, and the action information.

Assignees

• Fanuc Corp

Inventors

• Tsuneki Ryoutarou
• Ikai Satoshi
• Shimoda Takaki

Classifications

• G05B2219/33034

  Online learning, training · CPC title

• G05B13/0265 Primary

  the criterion being a learning criterion · CPC title

• H02P29/20

  for controlling one motor used for different sequential operations · CPC title

• G05B19/19

  characterised by positioning or contouring control systems, e.g. to control position from one programmed point to another or to control movement along a programmed continuous path · CPC title

• H02P2205/07

  Speed loop, i.e. comparison of the motor speed with a speed reference · CPC title