Deep hybrid state network with feature reinforcement for intelligent fault diagnosis of delta 3-D printers

Shaohui Zhang, Zhenzhong Sun, Chuan Li, Diego Cabrera, Jianyu Long, Yun Bai

Research output: Contribution to journalArticlepeer-review

17 Scopus citations

Abstract

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.

Original languageEnglish
Article number8728244
Pages (from-to)779-789
Number of pages11
JournalIEEE Transactions on Industrial Informatics
Volume16
Issue number2
DOIs
StatePublished - Feb 2020

Bibliographical note

Funding Information:
Manuscript received January 6, 2019; revised April 17, 2019 and May 9, 2019; accepted May 29, 2019. Date of publication June 3, 2019; date of current version January 14, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant 51605406, Grant 51775112, and Grant 71801046; and in part by the Natural Science Foundation of Guangdong Province under Grant 2018A030310029. Paper no. TII-19-0046 (Corresponding author: Jianyu Long.) S. Zhang, Z. Sun, C. Li, J. Long, and Y. Bai are with the School of Mechanical Engineering, Dongguan University of Technology, Dongguan 523808, China (e-mail:, zhangsh@dgut.edu.cn; drzzsun@sina.com; chuanli@dgut.edu.cn; longjy@dgut.edu.cn; baiyun@dgut.edu.cn).

Publisher Copyright:
© 2005-2012 IEEE.

Keywords

  • Deep hybrid state network (DHSN)
  • delta three-dimensional (3-D) printer
  • fault diagnosis
  • feature reinforcement

Fingerprint

Dive into the research topics of 'Deep hybrid state network with feature reinforcement for intelligent fault diagnosis of delta 3-D printers'. Together they form a unique fingerprint.

Cite this