AVMD and its application on incipient fault diagnosis of rolling bearings

Aiming at the problem that it is difficult to accurately extract the incipient fault features of rolling bearings, an incipient fault diagnosis method based on adaptive variational mode decomposition (AVMD) is proposed. Firstly, a new fault-impact measure index (FIMI) is established to guide the multi-strategy improved parrot algorithm (IPO) to adaptively obtain the optimal parameter combination K, α of VMD, so as to realize the accurate decomposition of fault signal. Secondly, the principal fault characteristic component is extracted based on the FIMI maximization criterion. Finally, the fault component undergoes enhanced envelope spectrum processing to identify the fault type. Numerical simulations and experimental data confirm the method’s effectiveness and feasibility for incipient fault diagnosis of rolling bearings, showcasing its superiority over existing techniques.