Experimental study on gearbox prognosis using total life vibration analysis

The wear fault is one of the gear failure modes which most frequently happen in gearboxes. Tracking the development of wear, especially estimating the remaining usage life for early wear is a challenge in gearbox fault diagnosis and prognosis. A method to extract the feature of gearbox's signal is proposed and the remaining usage life is evaluated in this paper. The total life vibration signal of experimental study is taken as the research basis. Extracting features from vibration signals is carried out by Time-Frequency analysis. The rule of gear wear progression is studied using the vibration signal feature. The remaining usage life estimate is implemented by Hidden semi-Markov model. Through the total life test of gearbox, the feasibility and effectiveness of this method is verified.