A novel pattern-frequency tree approach for transition analysis and anomaly detection in nonlinear and nonstationary systems

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The failure to identify anomaly patterns in dynamic systems can cause catastrophic events and incur a high cost. Prior research efforts attempted to use multiple sensors for a closer monitoring of the system dynamics. However, realizing full utilization of multiple sensors without the normality assumptions and dimensionality reduction remains a research challenge to build control schemes. This paper presents a novel methodology of pattern-frequency tree for transition analysis and anomaly detection in nonlinear and nonstationary systems. First, we propose Hyperoctree State space Aggregation Segmentation (HSAS) to delineate the high-dimensional dynamic processes in a continuous state space. Then, we develop a pattern-frequency tree to characterize and model the pattern distribution. Finally, we leverage pattern-frequency distribution information to develop a k-Maximin deviation algorithm for effective and efficient detection of process anomalies. Experimental results demonstrate that the proposed method performs better than the conventional methods in multi-sensor settings and high-dimensional environments.

Original languageEnglish (US)
Title of host publication67th Annual Conference and Expo of the Institute of Industrial Engineers 2017
PublisherInstitute of Industrial Engineers
Pages1264-1269
Number of pages6
ISBN (Electronic)9780983762461
StatePublished - 2017
Event67th Annual Conference and Expo of the Institute of Industrial Engineers 2017 - Pittsburgh, United States
Duration: May 20 2017May 23 2017

Other

Other67th Annual Conference and Expo of the Institute of Industrial Engineers 2017
CountryUnited States
CityPittsburgh
Period5/20/175/23/17

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering

Fingerprint Dive into the research topics of 'A novel pattern-frequency tree approach for transition analysis and anomaly detection in nonlinear and nonstationary systems'. Together they form a unique fingerprint.

  • Cite this

    Chen, C. B., Yang, H., & Tirupatikumara, S. R. (2017). A novel pattern-frequency tree approach for transition analysis and anomaly detection in nonlinear and nonstationary systems. In 67th Annual Conference and Expo of the Institute of Industrial Engineers 2017 (pp. 1264-1269). Institute of Industrial Engineers.