# US 2020/0262019 A1 · Cutting fluid amount adjusting device and system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0262019 A1
- Document ID: US20200262019A1
- Status: Published application
- Kind: A1
- Application number: 16/787,074
- Filed: 2020-02-11
- Published: 2020-08-20
- Earliest claimed: 2019-02-18
- Assignees: Fanuc Corporation
- Applicants: Fanuc Corporation
- Inventors: Shinichi OZEKI
- Web page: https://patentgrep.com/patent/US20200262019A1

## CPC

- B23Q 11/1038: {using cutting liquids with special characteristics, e.g. flow rate, quality}
- G06F 18/2155: {characterised by the incorporation of unlabelled data, e.g. multiple instance learning [MIL], semi-supervised techniques using expectation-maximisation [EM] or naïve labelling}
- G05B 13/027: {using neural networks only}
- B23Q: DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING (tools of the kind used in lathes or boring machines B23B27/00); MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)

## Abstract

A cutting fluid amount adjusting device acquires at least data indicating a machining state of a machine tool and data relating to cutting fluid supplied from a cutting fluid supplying device, creates data used in machine learning based on the acquired data, and executes, based on the created data, processing of the machine learning relating to the discharge amount of the cutting fluid from a cutting fluid nozzle in an environment in which machining of a workpiece by the machine tool is performed.

## Claims

### Claim 1

A cutting fluid amount adjusting device for adjusting a discharge amount of cutting fluid from at least one cutting fluid nozzle included in a cutting fluid supplying device for supplying the cutting fluid to a machining region of a machine tool for machining a workpiece, the cutting fluid amount adjusting device comprising:
a data acquirer configured to acquire at least data indicating a machining state by the machine tool and data relating to the cutting fluid supplied from the cutting fluid supplying device;
a preprocessor configured to create, based on the data acquired by the data acquirer, data used in machine learning; and
a machine learning device configured to execute, based on the data created by the preprocessor, processing of the machine learning relating to the discharge amount of the cutting fluid from the cutting fluid nozzle under an environment in which machining of the workpiece by the machine tool is performed.

### Claim 2 (depends on 1)

The cutting fluid amount adjusting device according to claim 1, wherein
the preprocessor creates, as data used in supervised learning by the machine learning device, state data containing at least tool data including information concerning a tool used in the machining of the workpiece by the machine tool, machining condition data including information concerning machining conditions in the machining of the workpiece by the machine tool, workpiece data including information concerning the workpiece machined by the machine tool, cutting fluid data including information concerning the cutting fluid supplied to the machining region of the machine tool by the cutting fluid supplying device, machining process data including information concerning a machining process of the workpiece by the machine tool, cutting fluid discharge position data including information concerning a discharge position of the cutting fluid by the cutting fluid nozzle and cutting fluid discharge amount data including an amount of the cutting fluid discharged from the cutting fluid nozzle included in the cutting fluid supplying device and label data containing at least discharge amount propriety data indicating propriety of the discharge amount of the cutting fluid discharged from the cutting fluid nozzle, and
the machine learning device includes a learner configured to generate, based on the state data and the label data, a learning model associating the machining state by the machine tool and a state of the cutting fluid supplied from the cutting fluid supplying device with the propriety of the discharge amount of the cutting fluid discharged from the cutting fluid nozzle.

### Claim 3 (depends on 1)

The cutting fluid amount adjusting device according to claim 1, wherein
the preprocessor creates, as data used in estimation by the machine learning device, state data containing at least tool data including information concerning a tool used in the machining of the workpiece by the machine tool, machining condition data including information concerning machining conditions in the machining of the workpiece by the machine tool, workpiece data including information concerning the workpiece machined by the machine tool, cutting fluid data including information concerning the cutting fluid supplied to the machining region of the machine tool by the cutting fluid supplying device, machining process data including information concerning a machining process of the workpiece by the machine tool, cutting fluid discharge position data including information concerning a discharge position of the cutting fluid by the cutting fluid nozzle and cutting fluid discharge amount data including an amount of the cutting fluid discharged from the cutting fluid nozzle included in the cutting fluid supplying device, and
the machine learning device includes:
a learning-model storage configured to store a learning model associating the machining state by the machine tool and a state of the cutting fluid supplied from the cutting fluid supplying device with propriety of the discharge amount of the cutting fluid discharged from the cutting fluid nozzle; and
an estimator configured to estimate, based on the state data, the propriety of the discharge amount of the cutting fluid discharged from the cutting fluid nozzle using the learning model stored in the learning-model storage, and
the cutting fluid amount adjusting device further comprises a discharge-amount determiner configured to search for a minimum discharge amount of the cutting fluid estimated as good by the estimator and determine the discharge amount of the cutting fluid obtained by the search as an amount of the cutting fluid discharged from the cutting fluid nozzle.

### Claim 4 (depends on 1)

The cutting fluid amount adjusting device according to claim 1, wherein
the preprocessor creates, as data used in supervised learning by the machine learning device, state data containing at least tool data including information concerning a tool used in the machining of the workpiece by the machine tool, machining condition data including information concerning machining conditions in the machining of the workpiece by the machine tool, workpiece data including information concerning the workpiece machined by the machine tool, cutting fluid data including information concerning the cutting fluid supplied to the machining region of the machine tool by the cutting fluid supplying device, machining process data including information concerning a machining process of the workpiece by the machine tool and cutting fluid discharge position data including information concerning a discharge position of the cutting fluid by the cutting fluid nozzle and label data containing at least appropriate discharge amount data including an amount of the cutting fluid discharged from the cutting fluid nozzle, and
the machine learning device includes a learner configured to generate, based on the state data and the label data, a learning model associating the machining state by the machine tool and a state of the cutting fluid supplied from the cutting fluid supplying device with the discharge amount of the cutting fluid discharged from the cutting fluid nozzle.

### Claim 5 (depends on 1)

The cutting fluid amount adjusting device according to claim 1, wherein
the preprocessor creates, as data used in estimation by the machine learning device, state data containing at least tool data including information concerning a tool used in the machining of the workpiece by the machine tool, machining condition data including information concerning machining conditions in the machining of the workpiece by the machine tool, workpiece data including information concerning the workpiece machined by the machine tool, cutting fluid data including information concerning the cutting fluid supplied to the machining region of the machine tool by the cutting fluid supplying device, machining process data including information concerning a machining process of the workpiece by the machine tool and cutting fluid discharge position data including information concerning a discharge position of the cutting fluid by the cutting fluid nozzle, and
the machine learning device includes:
a learning-model storage configured to store a learning model associating the machining state by the machine tool and a state of the cutting fluid supplied from the cutting fluid supplying device with the discharge amount of the cutting fluid discharged from the cutting fluid nozzle; and
an estimator configured to estimate, based on the state data, an amount of the cutting fluid discharged from the cutting fluid nozzle using the learning model stored in the learning-model storage, and
the cutting fluid amount adjusting device further comprises a discharge-amount determiner configured to determine the amount of the cutting fluid discharged from the cutting fluid nozzle based on an estimation result of the estimator.

### Claim 6 (depends on 1)

The cutting fluid amount adjusting device according to claim 1, wherein
the preprocessor creates, as data used in supervised learning by the machine learning device, state data containing at least tool data including information concerning a tool used in the machining of the workpiece by the machine tool, machining condition data including information concerning machining conditions in the machining of the workpiece by the machine tool, workpiece data including information concerning the workpiece machined by the machine tool, cutting fluid data including information concerning the cutting fluid supplied to the machining region of the machine tool by the cutting fluid supplying device, machining process data including information concerning a machining process of the workpiece by the machine tool, cutting fluid discharge position data including information concerning a discharge position of the cutting fluid by the cutting fluid nozzle, and cutting fluid discharge amount data including an amount of the cutting fluid discharged from the cutting fluid nozzle included in the cutting fluid supplying device and label data containing at least discharge amount propriety data indicating propriety of the discharge amount of the cutting fluid discharged from the cutting fluid nozzle, and
the machine learning device includes a learner including:
a first learner configured to generate, based on the state data and the label data, a first learning model associating the machining state by the machine tool and a state of the cutting fluid supplied from the cutting fluid supplying device with the propriety of the discharge amount of the cutting fluid discharged from the cutting fluid nozzle; and
a second learner configured to generate, based on a result of estimation processing performed using the first learning model generated by the first learner, a second learning model associating the machining state by the machine tool and the state of the cutting fluid supplied from the cutting fluid supplying device with the discharge amount of the cutting fluid discharged from the cutting fluid nozzle.

### Claim 7 (depends on 1)

The cutting fluid amount adjusting device according to claim 1, wherein
the preprocessor creates, as data used in reinforcement learning by the machine learning device, state data containing at least tool data including information concerning a tool used in the machining of the workpiece by the machine tool, machining condition data including information concerning machining conditions in the machining of the workpiece by the machine tool, workpiece data including information concerning the workpiece machined by the machine tool, cutting fluid data including information concerning the cutting fluid supplied to the machining region of the machine tool by the cutting fluid supplying device, machining process data including information concerning a machining process of the workpiece by the machine tool, cutting fluid discharge position data including information concerning a discharge position of the cutting fluid by the cutting fluid nozzle and cutting fluid discharge amount data including an amount of the cutting fluid discharged from the cutting fluid nozzle included in the cutting fluid supplying device and determination data containing at least discharge amount determination data for determining the discharge amount of the cutting fluid discharged from the cutting fluid nozzle and workpiece state determination data for determining a state of the workpiece, and
the machine learning device includes:
a learner configured to generate, based on the state data and the determination data, a learning model associating the machining state by the machine tool and a state of the cutting fluid supplied from the cutting fluid supplying device with an adjusting behavior for the discharge amount of the cutting fluid discharged from the cutting fluid nozzle; and
a decision maker configured to determine, based on the state data, adjustment of the discharge amount of the cutting fluid discharged from the cutting fluid nozzle performed using the learning model generated by the learner, and
the cutting fluid amount adjusting device further comprises a discharge-amount determiner configured to determine, based on the determination of the decision maker, the amount of the cutting fluid discharged from the cutting fluid nozzle.

### Claim 8

A system in which a plurality of devices are connected to one another via a network,
the plurality of devices comprising a first cutting fluid amount adjusting device configured to adjust a discharge amount of cutting fluid from at least one cutting fluid nozzle included in a cutting fluid supplying device supplying the cutting fluid to a machining region of a machine tool that machines a workpiece,
the first cutting fluid amount adjusting device including:
a data acquirer configured to acquire at least data indicating a machining state by the machine tool and data relating to the cutting fluid supplied from the cutting fluid supplying device;
a preprocessor configured to create, based on the data acquired by the data acquirer, data used in machine learning; and
a machine learning device configured to execute, based on the data created by the preprocessor, processing of the machine learning relating to the discharge amount of the cutting fluid from the cutting fluid nozzle in an environment in which machining of the workpiece by the machine tool is performed, wherein
the preprocessor creates, as data used in supervised learning by the machine learning device, state data containing at least tool data including information concerning a tool used in the machining of the workpiece by the machine tool, machining condition data including information concerning machining conditions in the machining of the workpiece by the machine tool, workpiece data including information concerning the workpiece machined by the machine tool, cutting fluid data including information concerning the cutting fluid supplied to the machining region of the machine tool by the cutting fluid supplying device, machining process data including information concerning a machining process of the workpiece by the machine tool, cutting fluid discharge position data including information concerning a discharge position of the cutting fluid by the cutting fluid nozzle and cutting fluid discharge amount data including an amount of the cutting fluid discharged from the cutting fluid nozzle included in the cutting fluid supplying device and label data containing at least discharge amount propriety data indicating propriety of the discharge amount of the cutting fluid discharged from the cutting fluid nozzle, and
the machine learning device includes a learner configured to generate, based on the state data and the label data, a learning model associating the machining state by the machine tool and a state of the cutting fluid supplied from the cutting fluid supplying device with the propriety of the discharge amount of the cutting fluid discharged from the cutting fluid nozzle.

### Claim 9 (depends on 8)

The cutting fluid amount adjusting system according to claim 8, wherein
the plurality of devices comprise a computer including the machine learning device,
the computer acquires at least one learning model generated by the learning in the learner of the first cutting fluid amount adjusting device; and
the machine learning device included in the computer performs optimization and streamlining based on the acquired learning model.

### Claim 10 (depends on 8)

The cutting fluid amount adjusting system according to claim 8, wherein
the plurality of devices comprise a second cutting fluid amount adjusting device different from the first cutting fluid amount adjusting device; and
a learning result by the learner included in the first cutting fluid amount adjusting device is shared by the second cutting fluid amount adjusting device.

### Claim 11 (depends on 8)

The cutting fluid amount adjusting system according to claim 8, wherein
the plurality of devices comprise a second cutting fluid amount adjusting device different from the first cutting fluid amount adjusting device; and
data observed in the second cutting fluid amount adjusting device is usable in the learning by the learner included in the first cutting fluid amount adjusting device via the network.

### Claim 12

A system in which a plurality of devices are connected to one another via a network,
the plurality of devices comprising a first cutting fluid amount adjusting device configured to adjust a discharge amount of cutting fluid from at least one cutting fluid nozzle included in a cutting fluid supplying device for supplying the cutting fluid to a machining region of a machine tool that machines a workpiece,
the first cutting fluid amount adjusting device including:
a data acquirer configured to acquire at least data indicating a machining state by the machine tool and data relating to the cutting fluid supplied from the cutting fluid supplying device;
a preprocessor configured to create, based on the data acquired by the data acquirer, data used in machine learning; and
a machine learning device configured to execute, based on the data created by the preprocessor, processing of the machine learning relating to the discharge amount of the cutting fluid from the cutting fluid nozzle in an environment in which machining of the workpiece by the machine tool is performed, wherein
the preprocessor creates, as data used in supervised learning by the machine learning device, state data containing at least tool data including information concerning a tool used in the machining of the workpiece by the machine tool, machining condition data including information concerning machining conditions in the machining of the workpiece by the machine tool, workpiece data including information concerning the workpiece machined by the machine tool, cutting fluid data including information concerning the cutting fluid supplied to the machining region of the machine tool by the cutting fluid supplying device, machining process data including information concerning a machining process of the workpiece by the machine tool and cutting fluid discharge position data including information concerning a discharge position of the cutting fluid by the cutting fluid nozzle and label data containing at least appropriate discharge amount data including an amount of the cutting fluid discharged from the cutting fluid nozzle, and
the machine learning device includes a learner configured to generate, based on the state data and the label data, a learning model associating the machining state by the machine tool and a state of the cutting fluid supplied from the cutting fluid supplying device with the discharge amount of the cutting fluid discharged from the cutting fluid nozzle.

### Claim 13 (depends on 12)

The cutting fluid amount adjusting system according to claim 12, wherein
the plurality of devices comprise a computer including the machine learning device,
the computer acquires at least one learning model generated by the learning in the learner of the first cutting fluid amount adjusting device; and
the machine learning device included in the computer performs optimization and streamlining based on the acquired learning model.

### Claim 14 (depends on 12)

The cutting fluid amount adjusting system according to claim 12, wherein
the plurality of devices comprise a second cutting fluid amount adjusting device different from the first cutting fluid amount adjusting device; and
a learning result by the learner included in the first cutting fluid amount adjusting device is shared with the second cutting fluid amount adjusting device.

### Claim 15 (depends on 13)

The cutting fluid amount adjusting system according to claim 13, wherein
the plurality of devices comprise a second cutting fluid amount adjusting device different from the first cutting fluid amount adjusting device; and
data observed in the second cutting fluid amount adjusting device is usable in the learning by the learner included in the first cutting fluid amount adjusting device via the network.
