Machine learning unit, spindle replacement judgment apparatus, control, machine tool, production system and machine learning method capable of judging the necessity of a spindle replacement

摘要

A machine learning unit capable of judging the necessity of replacing a spindle of a machine tool. A machine learning unit includes a status observation section that observes a status variable including machining volume data indicating a number of machined workpieces, machining accuracy data indicating a difference between an actual size of a machined workpiece and a size target value, break time data representing a period of interruption of the operation display the machine tool, and replacement determination data indicating a judgment result of a necessity of a spindle replacement; and a learning section provided with profit and loss data, comprising a gain per unit time or a loss per unit time generated by a production of the machined workpiece, and a loss per unit time, the is generated due to the spindle replacement. The session uses the win-and-lose data and the status variable and learns a condition associated with the spindle replacement.