IP Library › Granted Patent US 12,231,067
Granted Patent B2
US 12,231,067 · App. 18/115,550 · Granted Feb 18, 2025

Motor controller

Inventors: Yutaka Yamada (Fuchu Tokyo, JP); Koji Suzuki (Fuchu Tokyo, JP); Ken Tanabe (Ota Tokyo, JP)
Assignees: Kabushiki Kaisha Toshiba; Toshiba Electronic Devices & Storage Corporation
H02P23/16H02P23/0022
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,231,067
App. No.
18/115,550
Granted
Feb 18, 2025
Kind
B2
Abstract

A motor controller includes a first control circuit, a second control circuit, a determination circuit, and a command circuit. The first control circuit outputs a first control value based on a rule base from a command value of an angular velocity and a measured value of an angular velocity. The second control circuit outputs a second control value based on a learned model from the command value of the angular velocity and the measured value of the angular velocity. The determination circuit determines a state based on at least the second control value. The command circuit acquires and outputs a control command value from the first control value and the second control value based on a result determined by the determination circuit.

Claims (41)

1. A motor controller comprising:

a first control circuit that outputs a first control value based on a rule base from a command value of an angular velocity and a measured value of an angular velocity;

a second control circuit that outputs a second control value based on a learned model from the command value of the angular velocity and the measured value of the angular velocity;

a determination circuit that determines a state based on at least the second control value; and

a command circuit that acquires and outputs a control command value from the first control value and the second control value based on a result determined by the determination circuit.

2. The motor controller according to claim 1 , wherein

the command circuit outputs the second control value when the determination circuit does not detect an abnormality in the second control value, and

outputs the first control value when the determination circuit detects an abnormality in the second control value.

3. The motor controller according to claim 2 , wherein the determination circuit determines the state based on a difference between the first control value and the second control value.

4. The motor controller according to claim 1 , wherein the second control circuit outputs a difference from a control value based on the rule base as the second control value based on the learned model.

5. The motor controller according to claim 4 , wherein

the command circuit outputs a value obtained by adding the second control value to the first control value when the determination circuit does not detect an abnormality in the second control value, and

outputs the first control value when the determination circuit detects an abnormality in the second control value.

6. The motor controller according to claim 1 wherein

the learned model is a model learned by reinforcement learning, and

the determination circuit determines the state based on a reward output from the learned model.

7. The motor controller according to claim 1 , wherein

the learned model is a model that outputs likelihood together with the second control value, and

the determination circuit determines the state based on the likelihood.

8. The motor controller according to claim 1 , wherein the determination circuit compares a change in a measured value of an output current with a change in the second control value to determine the state.

9. The motor controller according to claim 8 , wherein the determination circuit determines the state based on whether a positive/negative sign of the change in the measured value of the output current matches a positive/negative sign of the change in the second control value.

10. The motor controller according to claim 8 , wherein the determination circuit determines the state based on a difference between a magnitude of the change in the measured value of the output current and a magnitude of the change in the second control value.

11. The motor controller according to claim 1 , wherein the command circuit outputs a speed control value of a motor.

12. The motor controller according to claim 1 , further comprising

a third control circuit that outputs a current control value based on the rule base from the first control value and a measured value of current, wherein

the second control circuit outputs the second control value based on the command value of the angular velocity, the measured value of the angular velocity, and the current control value.

13. The motor controller according to claim 1 , wherein the measured value is obtained based on information sensed by a sensor.

14. The motor controller according to claim 1 , wherein the measured value is estimated based on at least an output from the command circuit.

15. A motor controller comprising:

a first control circuit that outputs a first control value related to a speed control based on a rule base from a command value of an angular velocity and a measured value of an angular velocity;

a second control circuit that outputs a second control value related to a current control based on a learned model from the first control value and a measured value of current;

a third control circuit that outputs a third control value related to the current control based on the rule base from the first control value and the measured value of the current;

a determination circuit that determines a state based on at least the second control value; and

a command circuit that acquires and outputs a control command value related to current control from the second control value and the third control value based on a result determined by the determination circuit.

16. A motor controller comprising:

a processing circuit, wherein

the processing circuit receives a command value and a measured value,

acquires a first control value based on a rule base from the command value and the measured value,

acquires a second control value based on a learned model from the command value and the measured value,

determines a state based on at least the second control value, and

generates and outputs a control command signal from the first control value and the second control value based on the state that has been determined.

Assignments (2)
CORRECTIVE ASSIGNMENT TO CORRECT THE THE SECOND ASSIGNEE ADDRESS PREVIOUSLY RECORDED AT REEL: 062905 FRAME: 0177. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNEMTN. Recorded Apr 5, 2023
From: YAMADA, YUTAKA; SUZUKI, KOJI; TANABE, KEN
To: KABUSHIKI KAISHA TOSHIBA; TOSHIBA ELECTRONIC DEVICES & STORAGE CORPORATION
Reel/Frame 063257/0601 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 7, 2023
From: YAMADA, YUTAKA; SUZUKI, KOJI; TANABE, KEN
To: KABUSHIKI KAISHA TOSHIBA; TOSHIBA ELECTRONIC DEVICES & STORAGE CORPORATION
Reel/Frame 062905/0177 →
Priority Claims (1)
JP 2022-149340 · Sep 20, 2022 · national
Continuity (1)
Related Publication 20240097590A1 · Mar 21, 2024
References Cited (6)
US 10503130B2 · Ikai · 2019 [cited by examiner]
JP H05297904A · 1993 [cited by applicant]
JP 5088413B2 · 2012 [cited by applicant]
JP 6577508B2 · 2019 [cited by applicant]
WO 2010024194A1 · 2010 [cited by applicant]
https://www.researchgate.net/publication/339656951_Improve_PID_controller_through_reinforcement_learning. [cited by applicant]