Early bearing fault diagnosis based on improved SFLA and ELM network

Abstract

In this paper, an extreme learning machine (ELM) network based on an improved shuffled frog leaping algorithm (CCSFLA) is applied in early bearing fault diagnosis. ELM is a new type of single layer forward network. Although the generalization is stronger compared with traditional neural networks, a random setup of initial parameters increases instability of the network. An improved SFLA based on sinusoidal chaotic mapping with infinite collapses and constriction factors (CCSFLA) is proposed in this paper to optimize the ELM and obtain a CCSFLA–ELM model. Results show that the CCSFLA–ELM model can be used for optimization and that it improved the recognition of early bearing fault diagnosis.