TY - JOUR
T1 - Deep hybrid state network with feature reinforcement for intelligent fault diagnosis of delta 3-D printers
AU - Zhang, Shaohui
AU - Sun, Zhenzhong
AU - Li, Chuan
AU - Cabrera, Diego
AU - Long, Jianyu
AU - Bai, Yun
N1 - Publisher Copyright:
© 2005-2012 IEEE.
PY - 2020/2
Y1 - 2020/2
N2 - An echo state network (ESN) is a type of recurrent neural network that is good at processing time-series data with dynamic behavior. However, the use of ESNs to enhance fault-classification accuracy continues to be challenging when the condition signals are collected by low-cost sensors. In this paper, a deep network algorithm, called a deep hybrid state network (DHSN), is proposed for fault diagnosis of three-dimensional printers using attitude data with low measurement precision. In the DHSN, the output data of a sparse auto-encoder are regarded as the abstract features of a double-structured ESN (DESN). The DESN is designed for feature reinforcement and fault recognition, wherein the first function reinforces the features and the second is used for fault classification. More specifically, feature reinforcement is developed to improve the clustering performance and replace the traditional overall feedback fine-tuning in deep models. This strategy improves learning efficiency and overcomes the vanishing-gradient problem for deep learning. The forecasting performance of the proposed approach is evaluated in experiments, and its superiority is demonstrated through comparison with other intelligent fault-diagnosis technologies.
AB - An echo state network (ESN) is a type of recurrent neural network that is good at processing time-series data with dynamic behavior. However, the use of ESNs to enhance fault-classification accuracy continues to be challenging when the condition signals are collected by low-cost sensors. In this paper, a deep network algorithm, called a deep hybrid state network (DHSN), is proposed for fault diagnosis of three-dimensional printers using attitude data with low measurement precision. In the DHSN, the output data of a sparse auto-encoder are regarded as the abstract features of a double-structured ESN (DESN). The DESN is designed for feature reinforcement and fault recognition, wherein the first function reinforces the features and the second is used for fault classification. More specifically, feature reinforcement is developed to improve the clustering performance and replace the traditional overall feedback fine-tuning in deep models. This strategy improves learning efficiency and overcomes the vanishing-gradient problem for deep learning. The forecasting performance of the proposed approach is evaluated in experiments, and its superiority is demonstrated through comparison with other intelligent fault-diagnosis technologies.
KW - Deep hybrid state network (DHSN)
KW - delta three-dimensional (3-D) printer
KW - fault diagnosis
KW - feature reinforcement
UR - http://www.scopus.com/inward/record.url?scp=85078522052&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/2e17e0ed-249f-3978-975b-c2133f556d6c/
U2 - 10.1109/TII.2019.2920661
DO - 10.1109/TII.2019.2920661
M3 - Article
AN - SCOPUS:85078522052
SN - 1551-3203
VL - 16
SP - 779
EP - 789
JO - IEEE Transactions on Industrial Informatics
JF - IEEE Transactions on Industrial Informatics
IS - 2
M1 - 8728244
ER -