TY - JOUR
T1 - LiftingNet
T2 - A Novel Deep Learning Network with Layerwise Feature Learning from Noisy Mechanical Data for Fault Classification
AU - Pan, Jun
AU - Zi, Yanyang
AU - Chen, Jinglong
AU - Zhou, Zitong
AU - Wang, Biao
N1 - Publisher Copyright:
© 1982-2012 IEEE.
PY - 2018/6
Y1 - 2018/6
N2 - The key challenge of intelligent fault diagnosis is to develop features that can distinguish different categories. Because of the unique properties of mechanical data, predetermined features based on prior knowledge are usually used as inputs for fault classification. However, proper selection of features often requires expertise knowledge and becomes more difficult and time consuming when volume of data increases. In this paper, a novel deep learning network (LiftingNet) is proposed to learn features adaptively from raw mechanical data without prior knowledge. Inspired by convolutional neural network and second generation wavelet transform, the LiftingNet is constructed to classify mechanical data even though inputs contain considerable noise and randomness. The LiftingNet consists of split layer, predict layer, update layer, pooling layer, and full-connection layer. Different kernel sizes are allowed in convolutional layers to improve learning ability. As a multilayer neural network, deep features are learned from shallow ones to represent complex structures in raw data. Feasibility and effectiveness of the LiftingNet is validated by two motor bearing datasets. Results show that the proposed method could achieve layerwise feature learning and successfully classify mechanical data even with different rotating speed and under the influence of random noise.
AB - The key challenge of intelligent fault diagnosis is to develop features that can distinguish different categories. Because of the unique properties of mechanical data, predetermined features based on prior knowledge are usually used as inputs for fault classification. However, proper selection of features often requires expertise knowledge and becomes more difficult and time consuming when volume of data increases. In this paper, a novel deep learning network (LiftingNet) is proposed to learn features adaptively from raw mechanical data without prior knowledge. Inspired by convolutional neural network and second generation wavelet transform, the LiftingNet is constructed to classify mechanical data even though inputs contain considerable noise and randomness. The LiftingNet consists of split layer, predict layer, update layer, pooling layer, and full-connection layer. Different kernel sizes are allowed in convolutional layers to improve learning ability. As a multilayer neural network, deep features are learned from shallow ones to represent complex structures in raw data. Feasibility and effectiveness of the LiftingNet is validated by two motor bearing datasets. Results show that the proposed method could achieve layerwise feature learning and successfully classify mechanical data even with different rotating speed and under the influence of random noise.
KW - Convolutional neural network (CNN)
KW - deep learning
KW - intelligent fault diagnosis
KW - second generation wavelet transform (SGWT)
UR - https://www.scopus.com/pages/publications/85032735906
U2 - 10.1109/TIE.2017.2767540
DO - 10.1109/TIE.2017.2767540
M3 - 文章
AN - SCOPUS:85032735906
SN - 0278-0046
VL - 65
SP - 4973
EP - 4982
JO - IEEE Transactions on Industrial Electronics
JF - IEEE Transactions on Industrial Electronics
IS - 6
ER -