Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: A One-Class Support Vector Machine Calibration Method for Time Series Change Point Detection

Journal Article · · Prognostics and System Health Management Conference
 [1];  [2];  [3];  [1];  [1]
  1. Univ. of California, Berkeley, CA (United States)
  2. California Inst. of Technology (CalTech), Pasadena, CA (United States)
  3. National Univ. of Singapore (Singapore)
+ Show Author Affiliations

Identifying the change point of a system’s health status is critical. Indeed, a change point usually signifies an incipient fault under development. The One-Class Support Vector Machine (OC-SVM) is a popular machine learning model for anomaly detection that could be used for identifying change points; yet, it is sometimes difficult to obtain a good OC-SVM model that can be used on sensor measurement time series to identify the change points in system health status. In this paper, we propose a novel approach for calibrating OC-SVM models. Our method uses a heuristic search method to find a good set of input data and hyperparameters that yield a well-performing model. Our results on the C-MAPSS dataset demonstrate that OC-SVM can achieve satisfactory accuracy in detecting change point in time series with fewer training data, compared to state-of-the-art deep learning approaches. In our case study, the OC-SVM calibrated by the proposed model is shown to be useful especially in scenarios with limited amount of training data.

Research Organization:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
Sponsoring Organization:
USDOE Office of Science (SC); National Science Foundation (NSF)
Grant/Contract Number:
AC02-05CH11231
OSTI ID:
1572820
Journal Information:
Prognostics and System Health Management Conference, Vol. 2019; Conference: International Conference on Prognostics and Health Management (ICPHM), San Francisco, CA (United States), 17-20 June 2019; ISSN 2166-563X
Publisher:
IEEECopyright Statement
Country of Publication:
United States
Language:
English

References (9)

Optimization by Simulated Annealing journal May 1983
Recurrent neural networks for remaining useful life estimation conference October 2008
Long Short-Term Memory Network for Remaining Useful Life estimation conference June 2017
Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction conference January 2014
Estimating the Support of a High-Dimensional Distribution journal July 2001
Classification and Verification of Handwritten Signatures with Time Causal Information Theory Quantifiers journal December 2016
Detecting and Diagnosing Incipient Building Faults Using Uncertainty Information from Deep Neural Networks conference June 2019
Fuzzy/Bayesian change point detection approach to incipient fault detection journal March 2011
Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces journal January 1997

Cited By (3)

An Encoder-Decoder Based Approach for Anomaly Detection with Application in Additive Manufacturing conference December 2019
Are Ensemble Classifiers Powerful Enough for the Detection and Diagnosis of Intermediate-Severity Faults? preprint January 2020
Augmenting Monte Carlo Dropout Classification Models with Unsupervised Learning Tasks for Detecting and Diagnosing Out-of-Distribution Faults preprint January 2019

Similar Records

Related Subjects

42 ENGINEERING
97 MATHEMATICS AND COMPUTING
Support vector machine
change point detection