Numerical controller and machine learning device
A numerical controller has a machine learning device that performs machine learning of the adjustment of a setting value used in override control. The machine learning device acquires state data showing states of the numerical controller and a machine, sets reward conditions, calculates a reward based on the state data and the reward conditions, performs the machine learning of the adjustment of the setting value used in override control, and determines the adjustment of the setting value used in override control, based on a machine learning result and the state data.
1. A numerical controller controlling a machine including at least one axis, the numerical controller comprising:
a machine learning device that performs machine learning of an adjustment of an setting value used in override control of a motor that drives the axis, wherein
the machine learning includes a processor configured to:
acquire state data indicating states of the numerical controller and the machine and containing a current value of the setting value used in override control of the motor;
set reward conditions;
calculate a reward, based on the state data and the reward conditions;
perform the machine learning of the adjustment of the setting value used in override control; and
determine and outputs the adjustment of the setting value used in override control, based on the state data and a machine learning result of the adjustment of the setting value used in override control, and
perform the machine learning of the adjustment of the setting value used in override control, based on the adjusted setting value, the state data acquired after the adjustment of the setting value, and the reward.
2. The numerical controller according to claim 1 , wherein
the processor is further configured to calculate the reward, based on at least any of cycle time of an action of the machine, a load on a spindle of the machine, breakage of a tool attached to the machine, and machining accuracy of a workpiece machined by the machine.
3. The numerical controller according to claim 1 , which is connected to at least another numerical controller and which mutually exchanges or shares the machine learning result with this other numerical controller.
4. A machine learning device performing machine learning of an adjustment of setting value used in override control of a motor that drives at least one axis provided in a machine controlled by a numerical controller, the machine learning device comprising:
a processor configured to:
store a machine learning result of the adjustment of the setting value used in override control;
acquire state data indicating states of the numerical controller and the machine and containing a current value of a setting value used in override control of the motor;
set reward conditions;
calculate a reward, based on the state data and the reward conditions;
perform the machine learning of the adjustment of the setting value used in override control; and
determine and outputs the adjustment of the setting value used in override control, based on the state data and a machine learning result of the adjustment of the setting value used in override control, and
wherein the processor performs the machine learning of the adjustment of the setting value used in override control, based on the adjusted setting value, the state data acquired after the adjustment of the setting value, and the reward.