# US 2020/0394536 A1 · Machine learning device, prediction device, and control device

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

- Number: US 2020/0394536 A1
- Document ID: US20200394536A1
- Status: Published application
- Kind: A1
- Application number: 16/876,822
- Filed: 2020-05-18
- Published: 2020-12-17
- Earliest claimed: 2019-06-11
- Assignees: Fanuc Corporation
- Applicants: Fanuc Corporation
- Inventors: Shinichi OZEKI
- Web page: https://patentgrep.com/patent/US20200394536A1

## CPC

- G06N 5/04: Inference or reasoning models
- B29C 45/76: Measuring, controlling or regulating {(measuring in general G01; controlling or regulating in general G05)}
- B29C 45/7626: {the ejection or removal of moulded articles}
- G06N 20/00: Machine learning
- B29C 2945/76949: using a learning system, i.e. the system accumulates experience from previous occurrences, e.g. adaptive control
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- B29C: SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING (making preforms B29B11/00; making laminated products by combining previously unconnected layers which become one product whose layers will remain together B32B37/00 - B32B41/00)

## Abstract

Predicting a state of a mold after molding upon injection molding. A machine learning device includes: an input data acquiring unit that acquires input data including any molding condition including at least a type of resin, a type of additive, a blending ratio of the additive, and a temperature of the resin in molding any article molded by any injection molding machine, and state information indicating a wear amount of a mold before molding at the molding conditions; a label acquiring unit that acquires label data indicating state information of the mold after molding at the molding conditions included in the input data; and a learning unit that executes supervised learning using the input data acquired by the input data acquiring unit and the label data acquired by the label acquiring unit, and generates a learned model.

## Claims

### Claim 1

A machine learning device comprising:
an input data acquiring unit that acquires input data including any molding condition including at least a type of resin, a type of additive, a blending ratio of the additive, and a temperature of the resin in molding any article molded by any injection molding machine, and state information indicating a wear amount of a mold before molding at the molding conditions;
a label acquiring unit that acquires label data indicating state information of the mold after molding at the molding conditions included in the input data; and
a learning unit that executes supervised learning using the input data acquired by the input data acquiring unit and the label data acquired by the label acquiring unit, and generates a learned model.

### Claim 2 (depends on 1)

The machine learning device according to claim 1, wherein the molding condition includes information relating to the mold and/or information relating to the molded article.

### Claim 3 (depends on 1)

A prediction device comprising:
a learned model generated by a machine learning device according to claim 1;
an input unit that inputs, prior to molding by an injection molding machine, a molding condition to be performed and state information of a current mold; and
a prediction unit that inputs the molding condition to be performed and the state information of the current mold that are input by the input unit to the learned model, and predicts state information of the mold after molding at the molding condition to be performed.

### Claim 4 (depends on 3)

The prediction device according to claim 3, further comprising a determination unit that determines a period for replacing the mold on a basis of a comparison between a predicted value included in the state information of the mold predicted by the prediction unit and a threshold value that is set in advance.

### Claim 5 (depends on 4)

The prediction device according to claim 4, wherein, in a case of molding a plurality of articles on the basis of the molding condition to be performed and the state information of the current mold, the determination unit adjusts a number of articles to be molded so that the predicted value after molding the plurality of articles becomes smaller than the threshold value.

### Claim 6 (depends on 3)

The prediction device according to claim 3, wherein the learned model is provided in a server connected accessibly via a network from the prediction device.

### Claim 7 (depends on 1)

A prediction device comprising:
a machine learning device according to claim 1;
the learned model generated by the machine learning device;
an input unit that inputs, prior to molding by an injection molding machine, a molding condition to be performed and state information of a current mold; and
a prediction unit that inputs the molding condition to be performed and the state information of the current mold that are input by the input unit to the learned model, and predicts state information of the mold after molding at the molding condition to be performed.

### Claim 8 (depends on 3)

A control device comprising a prediction device according to claim 3.
