Machine tool for generating optimum acceleration/deceleration
AssigneeFanuc Corporation
InventorDaijirou Koga
Life of this patent
Estimating the term…
Abstract
A machine tool includes an operation evaluation section that evaluates an operation thereof and a machine learning device that performs the machine learning of a movement amount of an axis thereof. The machine learning device calculates a reward based on state data including the output of the operation evaluation section, performs the machine learning of the determination of the movement amount of the axis, and determines the movement amount of the axis based on a machine learning result and outputs the determined movement amount. The machine learning device performs the machine learning of the determination of the movement amount of the axis based on the determined movement amount of the axis, the acquired state data, and the calculated reward.
Claims6
A machine tool configured to drive at least one axis based on a command path of a tool commanded by a program to perform machining of a workpiece, the machine tool comprising:
- an operation evaluation section configured to evaluate an operation of the machine tool to output evaluation data;
- and
- a machine learning device configured to perform machine learning of a determination of a movement amount of the axis, wherein
- the machine learning device includes
- a state observation section configured to acquire, as state data, data including at least a position of the axis of the machine tool and the evaluation data output from the operation evaluation section,
- a reward conditions setting section configured to set a reward condition,
- a reward calculation section configured to calculate a reward based on the state data acquired by the state observation section,
- a movement-amount adjustment learning section configured to perform the machine learning of the determination of the movement amount of the axis, and
- a movement-amount output section configured to determine the movement amount of the axis such that acceleration of the tool becomes optimum, based on (i) a machine learning result of the machine learning of the determination of the movement amount of the axis by the movement-amount adjustment learning section and (ii) the state data, and output the determined movement amount, and
- the movement-amount adjustment learning section is configured to perform the machine learning of the determination of the movement amount of the axis based on (i) the determined movement amount of the axis, (ii) the state data acquired by the state observation section after an operation of the machine tool based on the output movement amount of the axis, and (iii) the reward calculated by the reward calculation section.
A simulation apparatus for simulating a machine tool configured to drive at least one axis based on a command path of a tool commanded by a program to perform machining of a workpiece, the simulation apparatus comprising:
- an operation evaluation section configured to evaluate a simulation operation of the machine tool to output evaluation data;
- and
- a machine learning device configured to perform machine learning of a determination of a movement amount of the axis, wherein
- the machine learning device includes
- a state observation section configured to acquire, as state data, simulated data including at least a position of the axis of the machine tool and the evaluation data output from the operation evaluation section,
- a reward calculation section configured to calculate a reward based on the state data acquired by the state observation section,
- a movement-amount adjustment learning section configured to perform the machine learning of the determination of the movement amount of the axis, and
- a movement-amount output section configured to determine the movement amount of the axis such that an acceleration of the tool becomes optimum, based on (i) a machine learning result of the machining learning of the determination of the movement amount of the axis by the movement-amount adjustment learning section and (ii) the state data, and output the determined movement amount, and
- the movement-amount adjustment learning section is configured to perform the machine learning of the determination of the movement amount of the axis based on (i) the determined movement amount of the axis, (ii) the state data acquired by the state observation section after the simulation operation of the machine tool based on the output movement amount of the axis, and (iii) the reward calculated by the reward calculation section.
A machine learning device configured to perform machine learning of a determination of a movement amount of at least one axis of a machine tool, the machine learning device comprising:
- a state observation section configured to acquire, as state data, data including at least a position of the axis of the machine tool;
- a reward conditions setting section configured to set reward condition;
- a reward calculation section configured to calculate a reward based on the state data acquired by the state observation section;
- a movement-amount adjustment learning section configured to perform the machine learning of the determination of the movement amount of the axis;
- and
- a movement-amount output section configured to determine the movement amount of the axis such that acceleration of a tool moving by the axis becomes optimum, based on (i) a machine learning result of the machine learning of the determination of the movement amount of the axis by the movement-amount adjustment learning section and (ii) the state data, and output the determined movement amount,
- wherein the movement-amount adjustment learning section is configured to perform the machine learning of the determination of the movement amount of the axis based on (i) the determined movement amount of the axis, (ii) the state data acquired by the state observation section after an operation of the machine tool based on the output movement amount of the axis, and (iii) the reward calculated by the reward calculation section.
Dependencies are inferred from the claim text.