Fault Diagnosis for Engine Based on Single-Stage Extreme Learning Machine

Abstract EN

Single-Stage Extreme Learning Machine (SS-ELM) is presented to dispose of the mechanical fault diagnosis in this paper.

Based on it, the traditional mapping type of extreme learning machine (ELM) has been changed and the eigenvectors extracted from signal processing methods are directly regarded as outputs of the network’s hidden layer.

Then the uncertainty that training data transformed from the input space to the ELM feature space with the ELM mapping and problem of the selection of the hidden nodes are avoided effectively.

The experiment results of diesel engine fault diagnosis show good performance of the SS-ELM algorithm.