Rail subduction amount prediction method, prediction device, rail repair time determination method, and rail subduction abnormality determination method

摘要

PROBLEM TO BE SOLVED: To predict a rail subduction amount which can appropriately predict a predicted value of a rail subduction amount at a specific position after a lapse of a predetermined period from the time when a bogie runs due to a secular change excluding the influence of fluctuation factors other than the secular change. Methods and predictors are provided. SOLUTION: In a method for predicting a rail subduction amount, a secular change rail subduction amount prediction model generated by machine-learning a plurality of training data is based on a secular change excluding the influence of fluctuation factors other than the secular change. The amount of change in the rail subduction amount y (t, p) at the specific position (p) during the trolley running (t) and the amount of change in the predetermined period (k) from the trolley running (t) of the influencing factors affecting the secular change. Enter the amount of change in the amount of rail subduction at a specific position (p) after a predetermined period (k) has elapsed from the time when the trolley runs due to aging (t) based on the aging, and from the time when the trolley runs due to aging (t) to the predetermined period (t) ( k) The predicted value y (t + k, p) of the rail subduction amount at the specific position (p) after the lapse is predicted (step S5). [Selection diagram] Fig. 4