Abstract: A method for labeling a data set of a supervised learning machine includes: calculating a deviation degree from a reference state A for each corresponding data in cases where a plurality of state estimation targets are in the reference state A and a reference state B; calculating a normalized deviation degree by taking a map of the deviation degree from A for each of the corresponding data with a map set for each of the state estimation targets. The map is allowed to map the deviation degree from A in A on a specified value to be output by the supervised learning machine in A; allowed to map the deviation degree from A in B on a specified value to be output by the supervised learning machine in B.

Abstract: A method for diagnosing an abnormality of rolling bearing includes: measuring a vibration of a rotator; performing a frequency analysis on the vibration to calculate a magnitude of a vibration at each frequency; calculating a characteristic frequency as a frequency of a vibration from a specification of the rolling bearing and a rotation speed of the rotator at a vibration measurement in the measuring; calculating a vibration value from which an effect of the rotation speed is removed by dividing a magnitude of a vibration at the characteristic frequency by a value including a base and an exponent, the base being a predetermined physical quantity in a proportional relation with an angular velocity of the rotator at the vibration measurement in the measuring, the exponent being a positive number; calculating an evaluation index based on the vibration value; and determining an existence of an abnormality based on the evaluation index.