Jin, Baihong and Tan, Yingshui and Nettekoven, Alexander and Chen, Yuxin and Topcu, Ufuk and Yue, Yisong and Sangiovanni Vincentelli, Alberto (2019) An Encoder-Decoder Based Approach for Anomaly Detection with Application in Additive Manufacturing. In: 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA). IEEE , Piscataway, NJ, pp. 1008-1015. ISBN 978-1-7281-4550-1. https://resolver.caltech.edu/CaltechAUTHORS:20190905-154317486
![]() |
PDF
- Submitted Version
See Usage Policy. 1MB |
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190905-154317486
Abstract
We present a novel unsupervised deep learning approach that utilizes an encoder-decoder architecture for detecting anomalies in sequential sensor data collected during industrial manufacturing. Our approach is designed to not only detect whether there exists an anomaly at a given time step, but also to predict what will happen next in the (sequential) process. We demonstrate our approach on a dataset collected from a real-world Additive Manufacturing (AM) testbed. The dataset contains infrared (IR) images collected under both normal conditions and synthetic anomalies. We show that our encoder-decoder model is able to identify the injected anomalies in a modern AM manufacturing process in an unsupervised fashion. In addition, our approach also gives hints about the temperature non-uniformity of the testbed during manufacturing, which was not previously known prior to the experiment.
Item Type: | Book Section | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Related URLs: |
| ||||||||||||
ORCID: |
| ||||||||||||
Additional Information: | © 2019 IEEE. This work is supported in part by the National Research Foundation of Singapore through a grant to the Berkeley Education Alliance for Research in Singapore (BEARS) for the Singapore-Berkeley Building Efficiency and Sustainability in the Tropics (SinBerBEST) program, and by the National Science Foundation under Grant No. 1645964 and 1646522. BEARS has been established by the University of California, Berkeley as a center for intellectual excellence in research and education in Singapore. Yuxin Chen is supported in part by a Swiss NSF Mobility Postdoctoral Fellowship and a PIMCO Fellowship. Baihong Jin and Yingshui Tan contributed equally to this paper. Alexander Nettekoven prepared and processed the experimental data. Dr. Yuxin Chen contributed to the theoretical aspects of this paper. | ||||||||||||
Funders: |
| ||||||||||||
Subject Keywords: | additive manufacturing, machine learning, anomaly detection, fault detection and diagnosis | ||||||||||||
DOI: | 10.1109/ICMLA.2019.00171 | ||||||||||||
Record Number: | CaltechAUTHORS:20190905-154317486 | ||||||||||||
Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20190905-154317486 | ||||||||||||
Official Citation: | Y. Tan et al., "An Encoder-Decoder Based Approach for Anomaly Detection with Application in Additive Manufacturing," 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), Boca Raton, FL, USA, 2019, pp. 1008-1015. doi: 10.1109/ICMLA.2019.00171 | ||||||||||||
Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | ||||||||||||
ID Code: | 98461 | ||||||||||||
Collection: | CaltechAUTHORS | ||||||||||||
Deposited By: | George Porter | ||||||||||||
Deposited On: | 05 Sep 2019 23:08 | ||||||||||||
Last Modified: | 16 Nov 2021 17:39 |
Repository Staff Only: item control page