Early intelligent fault diagnosis of rotating machinery based on IWOA-VMD and DMKELM

The effect of early fault vibration signals from rotating machinery is weak and easily drowned out by intense noise. Therefore, it still a great challenge to make diagnosis. An intelligent diagnosis method for proposed based on the parameter optimization variational mode decomposition (VMD) deep multi-kernel extreme learning machine (DMKELM). Firstly, improved whale algorithm (IWOA) designed introducing iterative chaotic mapping, nonlinear convergence factor inertia weight optimize VMD parameters. Secondly, optimized (OVMD) with sample entropy created reduce noise reconstruct signals. Finally, radial basis kernel function (RBF) polynomial (PK) are introduced construct mixed function, which can enhance classification performance generalization ability model. Two experiments bearings gears show that accuracy DMKELM 99 98.5%, respectively, at least 1% higher than comparative methods increases 4% after reduction. result shows has superiority in machinery.