Train running gear fault diagnosis method based on scale space guided fast spectrum correlation

A train running gear fault diagnosis method based on scale space guided fast spectrum correlation comprises the steps that high-speed train axle box vibration data of wheel set damage and bearing faults at different speeds are collected, and therefore an experiment data set containing different fault modes is obtained; processing the collected data through a fast spectrum correlation algorithm to obtain a fast spectrum coherence function; quantizing the spectrum coherence function through an L2/L1 norm standard to obtain a guide curve; performing frequency band division on the guide curve through a scale space method; and screening the divided frequency bands by applying fault quantitative indexes, selecting the frequency band with the most fault information of the wheel set and the axle box bearing, and carrying out enhanced envelope to obtain an enhanced envelope spectrum, thereby realizing accurate identification of the faults of the wheel set and the axle box bearing. According to the method, wheel set da