Tool selecting apparatus and machine learning device

A tool selecting apparatus comprising:

• a processor configured to
• observe, when machining of a workpiece is currently performed, data related to machining condition, data related to cutting condition, data related to machining result, as state variables indicative of a current environmental state of the machining of the workpiece,
• wherein the processor has learned distribution of the data related to the machining condition, the data related to the cutting condition, and the data related to the machining result, with respect to data related to a tool used in machining, the distribution being configured in a multi-dimensional space having axes indicating the data related to the machining condition, the data related to the cutting condition, the data related to the machining result, respectively,
• the processor has created different clusters for respective tool types each indicating a tool type-based trend of the learned distribution based on the learned distribution,
• the processor is further configured to
• determine priorities for the respective tool types based on cluster densities of the different clusters,
• determine a tool type that is usable under a condition designated by the state variables, based on the state variables and the tool type-based trend of the learned distribution,
• output the determined tool type, and
• control a machine tool and an actuator to use the determined tool type under the condition designated by the state variables.