Rail Local Damage Detection based on Recursive Frequency-domain Envelope Tracking Filter and Rail Impact Index

Rail local damages, including dislocation joint, dipped joint, joint gap and surface spalling, are frequently identified in real-life scenarios, yielding high noise, discomfort and even security issue of a train. In this study, a rail local damage detection method is proposed. First, the group delay of vibration impulse on wheel set is estimated with the use of squared envelope. Then, a novel dispersive signal decomposition method, recursive frequency-domain envelope tracking filter (RFETF), which reconstruct signal mode in frequency domain, is proposed for impulse extraction. The procedure of recovering different impulsive modes is executed iteratively rather than simultaneously, reducing the computation memory of algorithm. Finally, after extracting impulse response of vibration signal, the rail impact index (RII) is adopted for damage localization and health assessment. Results on real-life tram data demonstrate the proposed method is more effective than traditional time-related rail damage detecting methods.