Integrating Laplacian Eigenmaps Feature Space Conversion into Deep Neural Network for Equipment Condition Assessment

Abstract

Reliable equipment condition assessment technique is playing an increasingly important role in modern industry. This paper presents a novel method by integrating Laplacian Eigenmaps (LE) that transforms data features from original high-dimensional space to projected low-dimensional space to extract the more representative features into deep neural network (DNN) for equipment health assessment, in which the bearing run-to-failure data were investigated for validation studies. Through a series of comparison experiments with the original features, two other popular space transformation methods principal component analysis (PCA) and Isometric map (Isomap), and two other artificial intelligence algorithms hidden Markov model (HMM) and back-propagation neural network (BPNN), the proposed method in this paper was proved more effective for equipment condition evaluation.