Fault detection of planetary gearboxes based on an adaptive ensemble empirical mode decomposition

Planetary gearboxes are widely used in modern industry because of their advantages of large transmission ratio, strong load-bearing capacity, etc. Planetary gearboxes differ from fixed-axis gearboxes and exhibit unique behaviors, which increase the difficulty of fault detection. The vibration based signal processing technique is one of the principal tools for detecting gearbox faults. Empirical mode decomposition (EMD), as a time-frequency analysis technique, has been used to process nonlinear and non-stationary problems. But it has the shortcoming of mode mixing in decomposing signals. To overcome this shortcoming, ensemble empirical mode decomposition (EEMD) was proposed accordingly. EEMD can reduce the mode mixing to some extent. The performance of EEMD, however, depends on the parameters adopted in the EEMD algorithm. In current studies on EEMD, the parameters were generally selected artificially and subjectively. To solve the problem, a new adaptive ensemble empirical mode decomposition method is proposed in this chapter. In the method, the sifting number is adaptively selected and the amplitude of the added noise changes with the signal frequency during the decomposition process. Both simulations and a case of fault detection of a planetary gear demonstrate that the proposed method obtains the improved results compared with the original EEMD.