This work reports a novel method by fusing Laplacian Eigenmaps feature conversion and\ndeep neural network (DNN) for machine condition assessment. Laplacian Eigenmaps is adopted to\ntransform data features from original high dimension space to projected lower dimensional space,\nthe DNN is optimized by the particle swarm optimization algorithm, and the machine run-to-failure\nexperiment were investigated for validation studies. Through a series of comparative experiments\nwith the original features, two other effective space transformation techniques, Principal Component\nAnalysis (PCA) and Isometric map (Isomap), and two other artificial intelligence methods, hidden\nMarkov model (HMM) as well as back-propagation neural network (BPNN), the present method in\nthis paper proved to be more effective for machine operation condition assessment.
Loading....