Numerical control system
AssigneeFanuc Corporation
InventorsKazuhiro Satou, Kazunori Iijima
Life of this patent
Estimating the term…
Abstract
A numerical control system detects a state amount indicating a state of machining operation of a machine tool, creates a characteristic amount that characterizes the state of machining operation from the detected state amount, infers an evaluation value of the state of machining operation from the characteristic amount, and detects an abnormality in the state of machining operation on the basis of the inferred evaluation value. The numerical control system generates and updates a learning model by machine learning that uses the characteristic amount, and stores the learning model in correlation with a combination of conditions of the machining operation of the machine tool.
Claims13
A numerical control system that detects a state of wear or breakage of a tool of a machine tool that machines a workpiece, the numerical control system comprising:
- a condition designating unit that designates a condition of a machining operation of the machine tool;
- a state amount detection unit that detects a state amount indicating a state of the machining operation of the machine tool;
- an inference computing unit that infers an evaluation value of the state of machining operation, from the state amount;
- an abnormality detection unit that detects the state of wear or breakage of the tool on the basis of the evaluation value;
- a learning model generation unit that generates and updates a learning model by machine learning that uses the state amount;
- and
- a learning model storage unit that stores at least one learning model generated by the learning model generation unit in correlation with a combination of conditions designated by the condition designating unit, wherein
- the inference computing unit computes the evaluation value of the state of machining operation by selectively using at least one learning model among the learning models stored in the learning model storage unit on the basis of the condition of the machining operation designated by the condition designating unit.
A numerical control system that detects a state of wear or breakage of a tool of a machine tool that machines a workpiece, the numerical control system comprising:
- a condition designating unit that designates a condition of a machining operation of the machine tool;
- a state amount detection unit that detects a state amount indicating a state of the machining operation of the machine tool;
- an inference computing unit that infers an evaluation value of the state of machining operation of the machine tool, from the state amount;
- an abnormality detection unit that detects the state of wear or breakage of the tool on the basis of the evaluation value;
- and
- a learning model storage unit that stores at least one learning model which is correlated in advance with a combination of conditions of the machining operation of the machine tool, wherein
- the inference computing unit computes the evaluation value of the state of machining operation by selectively using at least one learning model among the learning models stored in the learning model storage unit, on the basis of the condition of the machining operation designated by the condition designating unit.
A method for detecting a state of a tool, comprising the steps of:
- designating a condition of a machining operation of a machine tool that machines a workpiece;
- detecting a state amount indicating a state of the machining operation of the machine tool;
- inferring an evaluation value of the state of machining operation from the state amount;
- detecting a state of wear or breakage of a tool on the basis of the evaluation value;
- and
- generating and updating a learning model by machine learning that uses the state amount, wherein
- in the inferring step, a learning model to be used is selected, on the basis of the condition of the machining operation designated in the step of designating the condition, among at least one learning model correlated in advance with a combination of conditions of the machining operation of the machine tool, and the evaluation value of the state of machining operation of the machine tool is computed using the selected learning model.
A method for detecting a state of a tool, comprising the steps of:
- designating a condition of a machining operation of a machine tool that machines a workpiece;
- detecting a state amount indicating a state of the machining operation of the machine tool;
- inferring an evaluation value of the state of machining operation from the state amount;
- and
- detecting a state of wear or breakage of a tool on the basis of the evaluation value, wherein
- in the inferring step, a learning model to be used is selected, on the basis of the condition of the machining operation designated in the step of designating the condition, among at least one learning model correlated in advance with a combination of conditions of the machining operation of the machine tool, and the evaluation value of the state of machining operation is computed using the selected learning model.
A learning model set in which each of a plurality of learning models is correlated with a combination of conditions of a machining operation of a machine tool, wherein
- each of the plurality of learning models is generated and updated on the basis of a state amount indicating a state of the machining operation performed under the condition of the machining operation of the machine tool, and
- one learning model is selected, on the basis of the condition set to the machine tool, among the plurality of learning models, and the selected learning model is used for a process of inferring an evaluation value of the state of machining operation of the machine tool.
Dependencies are inferred from the claim text.