IP Library › Granted Patent US 11,474,497
Granted Patent B2
US 11,474,497 · App. 17/620,744 · Granted Oct 18, 2022

Numerical control device, machine learning device, and numerical control method

Inventor: Masakazu Sagasaki (Tokyo, JP)
Assignee: MITSUBISHI ELECTRIC CORPORATION
G05B19/4093G05B19/4155G06N20/00
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 11,474,497
App. No.
17/620,744
Granted
Oct 18, 2022
Kind
B2
Abstract

A numerical control device for controlling a plurality of drive shafts to drive a tool and cause the tool to cut a workpiece while vibrating the tool in a fixed vibrating direction regardless of a cutting direction, a comparison unit that compares a command value of a cutting depth with an actual value of the cutting depth based on a vibration amplitude of the drive shaft when the vibrating direction and the cutting direction are not the same as each other, the cutting depth being a difference between a position of a face to be machined of the workpiece before machining and a position of the machined face after machining; and an adjustment unit that adjusts a movement of the tool so that the actual value becomes smaller when the actual value is larger than the command value.

Claims (25)

1. A numerical control device for controlling a plurality of drive shafts to drive a tool and cause the tool to cut a workpiece while vibrating the tool in a fixed vibrating direction regardless of a cutting direction, the cutting direction being a moving direction of the tool, the numerical control device comprising:

a first processor; and

a first memory to store a first program which, when executed by the first processor, performs processes of

determining whether or not the vibrating direction and the cutting direction are the same as each other;

comparing a command value of a cutting depth with an actual value of the cutting depth based on a vibration amplitude of the drive shaft when the vibrating direction and the cutting direction are not the same as each other, the cutting depth being a difference between a position of a face to be machined of the workpiece before machining and a position of the machined face after machining in the vibrating direction; and

adjusting a movement of the tool so that the actual value becomes smaller when the actual value is larger than the command value.

2. The numerical control device according to claim 1 , wherein the first processor further adjusts the vibration amplitude so that the actual value becomes equal to or smaller than the command value.

3. The numerical control device according to claim 1 , wherein the first processor further adjusts a movement path of the tool so that the actual value becomes equal to or smaller than the command value.

4. The numerical control device according to claim 1 , wherein the first processor further adjusts the vibration amplitude on the basis of a remaining distance to a point at which the cutting direction changes.

5. The numerical control device according to claim 1 , further comprising:

a machine learning device including:

a second processor; and

a second memory to store a second program which, when executed by the second processor, performs processes of:

observing, as state variables, machining program identification information for identifying a machining program describing procedures for controlling the drive shafts, machining path information indicating a machining path of the tool, tool identification information for identifying the tool, and offset information indicating an offset of the tool; and

learning the cutting depth in accordance with a data set created on the basis of the state variables.

6. The numerical control device according to claim 5 , wherein the first processor compares the actual value with a command value of the cutting depth indicated by a result of the learning.

7. A machine learning device for learning a command value of a cutting depth, the cutting depth being a difference between a face to be machined of a workpiece before machining and the machined face after machining in a fixed vibrating direction, in vibration cutting in which a plurality of drive shafts are controlled to drive a tool and cause the tool to machine the workpiece while vibrating the tool in the vibrating direction regardless of a cutting direction, the cutting direction being a moving direction of the tool, the machine learning device comprising:

a third processor; and

a third memory to store a third program which, when executed by the third processor, performs processes of:

observing, as state variables, machining program identification information for identifying a machining program describing procedures for controlling the drive shafts, machining path information indicating a machining path of the tool, and tool identification information for identifying the tool; and

learning the cutting depth for each cutting command in the machining program in accordance with a data set created on the basis of the state variables.

8. A numerical control method for controlling a plurality of drive shafts to drive a tool and cause the tool to cut a workpiece while vibrating the tool in a fixed vibrating direction regardless of a cutting direction, the cutting direction being a moving direction of the tool, the numerical control method comprising:

determining, whether or not the vibrating direction and the cutting direction are the same as each other;

comparing, a command value of a cutting depth with an actual value of the cutting depth based on a vibration amplitude of the drive shaft when the vibrating direction and the cutting direction are not the same as each other, the cutting depth being a difference between a position of a face to be machined of the workpiece before machining and a position of the machined face after machining in the vibrating direction; and

adjusting, a movement of the tool so that the actual value becomes smaller when the actual value is larger than the command value.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 20, 2021
From: SAGASAKI, MASAKAZU
To: MITSUBISHI ELECTRIC CORPORATION
Reel/Frame 058430/0509 →
Continuity (1)
Related Publication 20220269241A1 · Aug 25, 2022