Controller-equipped machining apparatus having machining time measurement function and on-machine measurement function
A machining apparatus is provided with a machine learning device that performs machine learning. The machine learning device performs the machine learning by receiving the input of machining accuracy between a machining shape of a workpiece measured on-machine and design data on the workpiece and machining time of the workpiece measured by a measurement device. Based on a result of the machine learning, the machining apparatus changes machining conditions such that the machining accuracy increases and the machining time becomes as short as possible.
1. A machining apparatus, comprising:
an on-machine measurement section configured to measure a machining shape of a workpiece on-machine;
a machining time measurement section configured to measure machining time of the workpiece; and
a machine learning device configured to perform machine learning based on inputs of (i) the machining time and (ii) machining accuracy between the machining shape and design data of the workpiece, wherein
the machine learning device is configured to change and output a machining condition based on a result of the machine learning such that the machining accuracy increases and the machining time becomes as short as possible in a range where the machining accuracy is maintained,
the machining apparatus is configured to perform machining of a workpiece in accordance with the machining condition output by the machine learning device, and
the machine learning device is configured to perform the machine learning based on a machining accuracy and a machining time that are obtained as a result of the machining of the workpiece by the machining apparatus in accordance with the machining condition output by the machine learning device.
2. The machining apparatus according to claim 1 , wherein
the machine learning device is configured to perform the machine learning in such a way that
a positive reward is given when the machining apparatus machines the workpiece such that an error between the machining shape and the design data of the workpiece is reduced or when the machining time is reduced, and
a negative reward is given when the machining apparatus machines the workpiece such that the error between the machining shape and the design data of the workpiece is increased or when the machining time is increased.
3. The machining apparatus according to claim 1 , wherein
the machine learning device is configured to perform, in the machine learning, weighting to indicate which of (i) reduction in an error between the machining shape and the design data of the workpiece and (ii) reduction in the machining time is to be emphasized.
4. The machining apparatus according to claim 1 , wherein
the machining apparatus is connectable to at least one another machining apparatus and configured to mutually exchange or share the result of the machine learning with the at least one another machining apparatus.
5. A machine learning device for performing machine learning of an adjustment of a machining condition in machining of a workpiece by a machining apparatus, the machine learning device comprising:
a learning result storage section configured to store a result of the machine learning of the adjustment of the machining condition;
a state observation section configured to acquire state data including at least machining time, machining accuracy of the workpiece, and the machining condition in the machining of the workpiece by the machining apparatus;
a machining condition adjustment learning section configured to adjust the machining condition based on the result of the machine learning of the adjustment of the machining condition and the state data acquired by the state observation section; and
a machining condition output section configured to output the machining condition adjusted by the machining condition adjustment learning section, wherein
the machining apparatus is configured to perform machining of a workpiece in accordance with the machining condition output by the machining condition output section, and
the machine learning device is configured to perform the machine learning based on a machining accuracy and a machining time that are obtained as a result of the machining of the workpiece by the machining apparatus in accordance with the machining condition output by the machining condition output section.
6. A system, comprising:
a plurality of machining apparatuses each as defined in claim 1 , wherein
the plurality of machining apparatuses respectively includes a plurality of machine learning devices, and
the plurality of machine learning devices is connected to each other via a network, and configured to
control the plurality of machining apparatuses, respectively, and
perform dispersed machine learning in a state where the plurality of machine learning devices is connected to each other via the network.
7. A system, comprising:
a plurality of machine learning devices each as defined in claim 5 ; and
a plurality of machining apparatuses, wherein
the plurality of machine learning devices is connected to each other via a network, and configured to
control the plurality of machining apparatuses, respectively, and
perform dispersed machine learning in a state where the plurality of machine learning devices is connected to each other via the network.