Controller and machine learning device

A controller that machines a workpiece by controlling a wire electrical discharge machine on the basis of a machining program, the controller comprising:

• a machine learning device that has learned a correction for a machining path of the machining with respect to a partial machining path, machining conditions and a machining environment of the machining, wherein
• the machine learning device includes:
• a state observation unit that observes, as state variables representing a current state of an environment, correction amount data indicating a correction amount for the machining path of the machining, machining path data indicating the partial machining path of the machining, machining condition data indicating the machining conditions of the machining, and machining environment data relating to the machining environment of the machining;
• a learning unit that learns the partial machining path, the machining conditions and the machining environment of the machining, and the correction for the machining path during the machining in association with each other;
• and
• an estimation result output unit that outputs the correction amount for the machining path on the basis of the state variables observed by the state observation unit and a learning result generated by the learning unit.

A machine learning device that learns, with respect to a partial machining path, machining conditions and a machining environment of machining performed by a wire electrical discharge machine that machines a workpiece on the basis of a machining program, a correction for a machining path of the machining, the machine learning device comprising:

• a state observation unit that observes, as state variables representing a current state of an environment, correction amount data indicating a correction amount for the machining path of the machining, machining path data indicating the partial machining path of the machining, machining condition data indicating the machining conditions of the machining, and machining environment data relating to the machining environment of the machining;
• a determination data acquisition unit that acquires, as determination data, machining accuracy determination data indicating an appropriateness determination result relating to a machining accuracy realized when machining is performed on the basis of the machining path corrected by the correction amount, and machining time determination data indicating an appropriateness determination result relating to a machining time required to perform machining on the basis of the machining path corrected by the correction amount;
• and
• a learning unit that uses the state variables and the determination data to learn the partial machining path, the machining conditions and the machining environment of the machining, and the correction for the machining path during the machining in association with each other.

A machine learning device that has learned, with respect to a partial machining path, machining conditions and a machining environment of machining performed by a wire electrical discharge machine that machines a workpiece on the basis of a machining program, a correction for a machining path of the machining, the machine learning device comprising:

• a state observation unit that observes, as state variables representing a current state of an environment, correction amount data indicating a correction amount for the machining path of the machining, machining path data indicating the partial machining path of the machining, machining condition data indicating the machining conditions of the machining, and machining environment data relating to the machining environment of the machining;
• a learning unit that learns the partial machining path, the machining conditions and the machining environment of the machining, and the correction for the machining path during the machining in association with each other;
• and
• an estimation result output unit that outputs the correction amount for the machining path on the basis of the state variables observed by the state observation unit and a learning result generated by the learning unit.