Back to results
US 11,583,968 B2Granted
Machine learning device, prediction device, and controller
AssigneeFanuc Corporation
InventorShinichi Ozeki
Life of this patent
Estimating the term…
Abstract
The state of a cutting fluid after machining is predicted. A machine learning device includes: an input data acquisition unit that acquires input data including arbitrary machining conditions for an arbitrary work in machining by an arbitrary machine tool and state information indicating a state of a cutting fluid before machining is performed under the machining conditions; a label acquisition unit that acquires label data indicating state information of the cutting fluid after the machining is performed under the machining conditions 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 to generate a learned model.
Claims12
A machine learning device comprising:
- an input data acquisition unit that acquires input data including arbitrary machining conditions for an arbitrary work in machining by an arbitrary machine tool and state information indicating a state of a cutting fluid before machining is performed under the machining conditions, the machining conditions including at least a machining time, a machining type, a size of the work, a number of works to be machined, a material, and a tool type;
- a label acquisition unit that acquires label data indicating state information of the cutting fluid after the machining is performed under the machining conditions included in the input data;
- 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 which predicts state information of the cutting fluid after machining;
- an input unit that inputs machining conditions to be performed from now on with respect to a machining target work and present state information of the cutting fluid prior to machining by the machine tool;
- a prediction unit that inputs the machining conditions to be performed from now on and the present state information input by the input unit to the learned model and predicts the state information of the cutting fluid after machining is performed under the machining conditions to be performed from now on;
- and
- a determination unit that (i) calculates an evaluation value by multiplying each of a plurality of weighting coefficients by a corresponding one of a plurality of predicted values included in the state information of the cutting fluid predicted by the prediction unit to obtain a plurality of weighted predicted values, and adding the plurality of weighted predicted values, and (ii) determines a timing to entirely replace the cutting fluid on the basis of a comparison between the calculated evaluation value and a threshold set in advance.
4 more elements
A prediction device comprising:
- a storage unit that stores a learned model, which predicts state information of a cutting fluid after machining, generated by a machine learning device, the machine learning device including:
- an input data acquisition unit that acquires input data including arbitrary machining conditions for an arbitrary work in machining by an arbitrary machine tool and state information indicating a state of the cutting fluid before machining is performed under the machining conditions, the machining conditions including at least a machining time, a machining type, a size of the work, a number of works to be machined, a material, and a tool type;
- a label acquisition unit that acquires label data indicating state information of the cutting fluid after the machining is performed under the machining conditions 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 which predicts state information of the cutting fluid after machining;
- an input unit that inputs machining conditions to be performed from now on with respect to a machining target work and present state information of the cutting fluid prior to machining by the machine tool;
- a prediction unit that inputs the machining conditions to be performed from now on and the present state information input by the input unit to the learned model and predicts the state information of the cutting fluid after machining is performed under the machining conditions to be performed from now on;
- and
- a determination unit that (i) calculates an evaluation value by multiplying each of a plurality of weighting coefficients by a corresponding one of a plurality of predicted values included in the state information of the cutting fluid predicted by the prediction unit to obtain a plurality of weighted predicted values, and adding the plurality of weighted predicted values, and (ii) determines a timing to entirely replace the cutting fluid on the basis of a comparison between the calculated evaluation value and a threshold set in advance.
6 more elements
A machine learning device comprising:
- an input data acquisition unit that acquires input data including arbitrary machining conditions for an arbitrary work in machining by an arbitrary machine tool and state information indicating a state of a cutting fluid before machining is performed under the machining conditions, the machining conditions including at least a machining time, a machining type, a size of the work, a number of works to be machined, a material, and a tool type;
- a label acquisition unit that acquires label data indicating state information of the cutting fluid after the machining is performed under the machining conditions included in the input data;
- 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 which predicts state information of the cutting fluid after machining;
- an input unit that inputs machining conditions to be performed from now on with respect to a machining target work and present state information of the cutting fluid prior to machining by the machine tool;
- a prediction unit that inputs the machining conditions to be performed from now on and the present state information input by the input unit to the learned model and predicts the state information of the cutting fluid after machining is performed under the machining conditions to be performed from now on;
- and
- a determination unit that (i) calculates an evaluation value by multiplying each of a plurality of weighting coefficients by a corresponding one of a plurality of predicted values included in the state information of the cutting fluid predicted by the prediction unit to obtain a plurality of weighted predicted values, and adding the plurality of weighted predicted values, and (ii) determines a timing to perform maintenance of the cutting fluid or a timing to entirely replace the cutting fluid on the basis of a comparison between the calculated evaluation value and a threshold set in advance.
4 more elements
A prediction device comprising:
- a storage unit that stores a learned model, which predicts state information of a cutting fluid after machining, generated by a machine learning device, the machine learning device including:
- an input data acquisition unit that acquires input data including arbitrary machining conditions for an arbitrary work in machining by an arbitrary machine tool and state information indicating a state of the cutting fluid before machining is performed under the machining conditions, the machining conditions including at least a machining time, a machining type, a size of the work, a number of works to be machined, a material, and a tool type;
- a label acquisition unit that acquires label data indicating state information of the cutting fluid after the machining is performed under the machining conditions 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 which predicts state information of the cutting fluid after machining;
- an input unit that inputs machining conditions to be performed from now on with respect to a machining target work and present state information of the cutting fluid prior to machining by the machine tool;
- a prediction unit that inputs the machining conditions to be performed from now on and the present state information input by the input unit to the learned model and predicts the state information of the cutting fluid after machining is performed under the machining conditions to be performed from now on;
- and
- a determination unit that (i) calculates an evaluation value by multiplying each of a plurality of weighting coefficients by a corresponding one of a plurality of predicted values included in the state information of the cutting fluid predicted by the prediction unit to obtain a plurality of weighted predicted values, and adding the plurality of weighted predicted values, and (ii) determines a timing to perform maintenance of the cutting fluid or a timing to entirely replace the cutting fluid on the basis of a comparison between the calculated evaluation value and a threshold set in advance.
6 more elements
Dependencies are inferred from the claim text.