Tool state estimation apparatus and machine tool

Patent metadata

Field	Value
Publication number	US-2018246494-A1
Application number	US-201815902560-A
Country	US
Kind code	A1
Filing date	Feb 22, 2018
Priority date	Feb 24, 2017
Publication date	Aug 30, 2018
Grant date	—

Abstract

A scattering direction, a scattering range, a scattering speed, or the like of chip generated by machining is acquired by image pickup unit, and a state (such as wearing and fracture) of a tool is estimated from the acquired dynamic information. A machine learning device is used to perform the estimation and the machine learning device is caused to learn a state of a tool relative to the combination of a plurality of dynamic information on the vicinity of the tool, and the state of the tool is estimated based on a result of the learning.

First claim

1 . A tool state estimation apparatus estimating a state of a tool used by a machine tool to machine a workpiece,
the tool state estimation apparatus comprising:
a state observation section that acquires dynamic information on the vicinity of the tool from log data acquired during an operation of the machine tool and generates input data based on the acquired dynamic information on the vicinity of the tool;
a learning section that performs machine learning using the input data generated by the state observation section to construct a learning model; and
a learning model storage section that stores the constructed learning model.

2 . The tool state estimation apparatus according to claim 1 , further comprising:
a label acquisition section that acquires, from the log data acquired during the operation of the machine tool, the teacher data indicating the state of the tool corresponding to the input data generated by the state observation section, wherein the learning section is configured to perform supervised learning using the input data generated by the state observation section and the teacher data acquired by the label acquisition section to construct a learning model.

3 . The tool state estimation apparatus according to claim 1 , wherein
the learning section is configured to perform unsupervised learning using the input data generated by the state observation section to construct a learning model in which a cluster based on the dynamic information on the vicinity of the tool is generated.

4 . A tool state estimation apparatus estimating a service life of a tool used by a machine tool to machine a workpiece,
the tool state estimation apparatus comprising:
a learning model storage section that stores a learning model constructed by machine learning based on dynamic information on the vicinity of the tool acquired during an operation of the machine tool;
a state observation section that acquires dynamic information on the vicinity of the tool from log data acquired during the operation of the machine tool and generates input data based on the acquired dynamic information on the vicinity of the tool; and
an estimation section that estimates a state of the tool from the input data generated by the state observation section using the learning model.

5 . The tool state estimation apparatus according to claim 1 , wherein
the dynamic information on the vicinity of the tool is information on an image indicating a scattering state of chip generated by machining of the machine tool.

6 . A machine tool comprising:
an alert section that issues an alert based on an estimation result of the state of the tool by the tool state estimation apparatus according to claim 4 .

Assignees

• Fanuc Corp

Inventors

• Nakahama Yasuhiro

Classifications

• G06N3/045

  Combinations of networks · CPC title

• B23Q17/0995

  Tool life management · CPC title

• G05B19/4065 Primary

  Monitoring tool breakage, life or condition · CPC title

• G05B19/4083

  Adapting program, configuration · CPC title

• G06N3/02

  Neural networks · CPC title