An improved method for fault diagnosis of rolling bearings of power generation equipment in a smart microgrid

In the construction of smart microgrids for petrochemical enterprises, generating unit is an important part, and rolling bearings are one key components generator. The condition bearing directly affects safe operation entire accurate fault diagnosis not only can improve stability microgrid, but also reduce risk loss factory. This study proposes improved method based on variational modal decomposition (VMD) a convolutional neural network (CNN). VMD algorithm was used to remove random noise in original signal CNN extract useful data from vibration processed by VMD. Since number penalty parameter difficult choose they have profound impact results, differential evolution (DE) as optimization envelope entropy fitness function optimize parameters. it ensure best fit hyper-parameters CNN, this using DE obtain suitable then diagnose fault. test results Case Western Reserve University show that combination convergence speed more than 10% accuracy over 99.6%.