Dressing estimation device and controller

Patent metadata

Field	Value
Publication number	US-11958166-B2
Application number	US-202016826952-A
Country	US
Kind code	B2
Filing date	Mar 23, 2020
Priority date	Apr 19, 2019
Publication date	Apr 16, 2024
Grant date	Apr 16, 2024

Abstract

An optimal timing to perform dressing on a grindstone is detected easily. A machine learning device includes: an input data acquisition unit that acquires input data including an arbitrary grinding condition for an arbitrary work material in a grinding process of an arbitrary grinding machine and grindstone information related to an arbitrary grindstone including at least a degree of necessity of dressing process indicating a degree of necessity of dressing before a grinding process is performed under the grinding condition; a label acquisition unit that acquires label data indicating the degree of necessity of dressing process of the grindstone after the grinding process is performed under the grinding condition included in the input data; and a learning unit that executes supervised learning using the input data acquired by the input data acquisition unit and the label data acquired by the label acquisition unit, and generates a learned model.

First claim

What is claimed is:

1. A dressing estimation device comprising:
a learned model generated by the machine learning device;
an input unit that inputs a grinding condition for a grinding target work material related to the grinding process and a grindstone ID indicating a grindstone selected by an operator to be used in a grinding process of a grinding machine prior to the grinding process of the grinding machine and grindstone information related to the grindstone to be used in the grinding process, including at least the present degree of necessity of dressing process based on the input grindstone ID and a grindstone management table stored in a storage unit of the dressing estimation device;
an estimation unit that estimates a degree of necessity of dressing process after the grinding process is performed under the grinding condition related to the grinding process with respect to the grindstone to be used in the grinding process, input by the input unit using the learned model; and
a determination unit that determines that the grinding condition related to the grinding process is to be changed so that the degree of necessity of dressing process of the grindstone does not exceed a threshold set in advance when the degree of necessity of dressing process of the grindstone estimated by the estimation unit exceeds the threshold,
wherein the machine learning device comprises:
an input data acquisition unit that acquires input data including an arbitrary grinding condition for an arbitrary work material in a grinding process of an arbitrary grinding machine and grindstone information related to an arbitrary grindstone including at least a degree of necessity of dressing process indicating a degree of necessity of dressing before a grinding process is performed under the grinding condition;
a label acquisition unit that acquires label data indicating the degree of necessity of dressing process of the grindstone after the grinding process is performed under the grinding condition included in the input data; and
a learning unit that executes supervised learning using the input data acquired by the input data acquisition unit and the label data acquired by the label acquisition unit, and generates the learned model.

2. The dressing estimation device according to claim 1 , wherein the grinding condition includes a grinding time for one or more work materials.

3. The dressing estimation device according to claim 1 , wherein
the determination unit adjusts the number of grinding target work materials included in the grinding condition.

4. The dressing estimation device according to claim 1 , wherein
the learned model is provided in a server connected so as to be accessible from the dressing estimation device via a network.

5. A dressing estimation device comprising:
a machine learning device;
a learned model generated by the machine learning device;
an input unit that inputs a grinding condition for a grinding target work material related to the grinding process and a grindstone ID indicating a grindstone selected by an operator to be used in a grinding process of a grinding machine prior to the grinding process of the grinding machine and grindstone information related to the grindstone to be used in the grinding process, including at least the present degree of necessity of dressing process based on the input grindstone ID and a grindstone management table stored in a storage unit of the dressing estimation device;
an estimation unit that estimates a degree of necessity of dressing process after the grinding process is performed under the grinding condition related to the grinding process with respect to the grindstone to be used in the grinding process, input by the input unit using the learned model; and
a determination unit that determines that the grinding condition related to the grinding process is to be changed so that the degree of necessity of dressing process of the grindstone does not exceed a threshold set in advance when the degree of necessity of dressing process of the grindstone estimated by the estimation unit exceeds the threshold,
wherein the machine learning device comprises:
an input data acquisition unit that acquires input data including an arbitrary grinding condition for an arbitrary work material in a grinding process of an arbitrary grinding machine and grindstone information related to an arbitrary grindstone including at least a degree of necessity of dressing process indicating a degree of necessity of dressing before a grinding process is performed under the grinding condition;
a label acquisition unit that acquires label data indicating the degree of necessity of dressing process of the grindstone after the grinding process is performed under the grinding condition included in the input data; and
a learning unit that executes supervised learning using the input data acquired by the input data acquisition unit and the label data acquired by the label acquisition unit, and generates the learned model.

6. A controller comprising a dressing estimation device,
wherein the dressing estimation device comprises:
a learned model generated by a machine learning device;
an input unit that inputs a grinding condition for a grinding target work material related to the grinding process and a grindstone ID indicating a grindstone selected by an operator to be used in a grinding process of a grinding machine prior to the grinding process of the grinding machine and grindstone information related to the grindstone to be used in the grinding process, including at least the present degree of necessity of dressing process based on the input grindstone ID and a grindstone management table stored in a storage unit of the dressing estimation device;
an estimation unit that estimates a degree of necessity of dressing process after the grinding process is performed under the grinding condition related to the grinding process with respect to the grindstone to be used in the grinding process, input by the input unit using the learned model; and
a determination unit that determines that the grinding condition related to the grinding process is to be changed so that the degree of necessity of dressing process of the grindstone does not exceed a threshold set in advance when the degree of necessity of dressing process of the grindstone estimated by the estimation unit exceeds the threshold,
wherein the machine learning device comprises:
an input data acquisition unit that acquires input data including an arbitrary grinding condition for an arbitrary work material in a grinding process of an arbitrary grinding machine and grindstone information related to an arbitrary grindstone including at least a degree of necessity of dressing process indicating a degree of necessity of dressing before a grinding process is performed under the grinding condition;
a label acquisition unit that acquires label data indicating the degree of necessity of dressing process of the grindstone after the grinding process is performed under the grinding condition included in the input data; and
a learning unit that executes supervised learning using the input data acquired by the input data acquisition unit and the label data acquired by the label acquisition unit, and generates the learned model.

Assignees

• Fanuc Corp

Inventors

• Ozeki Shinichi

Classifications

• G06N20/00 Primary

  Machine learning · CPC title

• B24B53/08 Primary

  controlled by information means, e.g. patterns, templets, punched tapes or the like · CPC title