MACHINE LEARNING APPARATUS FOR OPTIMIZING CYCLE PROCESSING TIME OF PROCESSING MACHINE, MOTOR CONTROL APPARATUS, PROCESSING MACHINE, AND MACHINE LEARNING METHOD

摘要

A machine learning apparatus includes a state observing unit and a learning unit. The state observation unit observes, during repeated processing operations, a state variable including a processing downtime and at least one of an actual one-cycle processing time of a processing machine and the temperature of a motor. The learning unit learns a value for selecting, based on the state variable and an overheat alarm level, the shortest processing downtime, which satisfies the fact that the temperature of the motor does not exceed the overheat alarm level when the repeated processing operations are performed.

主权项

1. A machine learning apparatus that is adapted to determine a processing downtime of a one-cycle processing time comprised of a one-cycle processing operation time and the processing downtime of a processing machine, so that the temperature of a motor for performing repeated processing operations of the processing machine does not exceed a predetermined temperature threshold, comprising:
a state observation unit which is adapted to observe, during the repeated processing operations, a state variable including the processing downtime and at least one of an actual one-cycle processing time of the processing machine and the temperature of the motor; and a learning unit which is adapted to learn a value for selecting, based on the state variable and the temperature threshold, the shortest processing downtime, in which the temperature of the motor does not exceed the temperature threshold when the repeated processing operations are performed.