Sep 12, 2019 ¡¤ It indicates that the sequential data after dimension reduction via the RNN-based VAE still can maintain the high-dimensional data information.

ABSTRACT In most of the fault detection methods, the time domain signals collected from the mechanical equipment usually need to be transformed into ...

In the first stage, the method RNN-based VAE was proposed which is highly suitable for dimension reduction of time series data. In addition to reducing the ...

This work proposed a two-stage machine learning analysis architecture which can accurately predict the motor fault modes only by using motor vibration ...

øöð¹: Motor Fault Detection and Feature Extraction Using RNN-Based Variational Autoencoder ; íÂíº: Huang, Yang ¡¤ Chen, Chiun-Hsun ¡¤ Huang, Chi-Jui ¡¤ ѦÌþÍïïïùÊͧ

Chen et al. designed a multiple two-layer sparse autoencoder (SAE) neural networks for feature fusion from multi-sensors and detect the faults of a rotating ...

A stacked supervised auto-encoder is proposed to pretrain the deep network and obtain deep fault-relevant features from raw input data.

Jul 21, 2024 ¡¤ This paper covers four traditional types of deep learning models: deep belief networks (DBN), autoencoders (AE), convolutional neural networks (CNN), and ...

Jun 12, 2024 ¡¤ This paper proposed a FD method based on variational autoencoder and semi-supervised learning for wind turbines bearings, which can solve the problem of ...