A novel pattern classification integrated GLPP with improved AROMF for fault diagnosis

Yuan Xu, Xue Jiang, Wei Ke, Qunxiong Zhu, Yanlin He, Yang Zhang, Zixu Wang

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

With the scale expansion of industrial processes, safety has become one of its important links and the requirements for safety monitoring are getting higher. How to realize timely and effective fault diagnosis, especially for incipient faults, has attracted more discussion and research. This paper proposes a novel pattern classification integrated global−local preserving projections (GLPP) and improved adaptive rank-order morphological filter (IAROMF) for fault diagnosis. First, in order to preserve the global manifold information and local manifold information of the data, GLPP is introduced to extract the features of the data to obtain the test signal and the template signal. Second, AROMF transformation is performed on the test signal and template signal to obtain the output trend feature. Third, as the pattern matching by Euclidean distance-based AROMF has the restriction of sequence timing and the feature points need to be strictly corresponding, the Weighted Dynamic Time Warping (WDTW) distance is used to calculate the total error of iteration between the template trend and the output trend. In order to prove the effectiveness of the method proposed in this paper, a case study was carried out on the Tennessee Eastman (TE) process. The experiment results illustrated that the novel pattern classification method proposed in this paper has higher diagnostic accuracy than other fault diagnosis methods, especially for incipient faults.

Original languageEnglish
Pages (from-to)299-311
Number of pages13
JournalProcess Safety and Environmental Protection
Volume171
DOIs
Publication statusPublished - Mar 2023

Keywords

  • AROMF
  • Fault diagnosis
  • GLPP
  • Pattern classification
  • WDTW distance

Fingerprint

Dive into the research topics of 'A novel pattern classification integrated GLPP with improved AROMF for fault diagnosis'. Together they form a unique fingerprint.

Cite this