DeepNAP: Deep neural anomaly pre-detection in a semiconductor fab

Chunggyeom Kim, Jinhyuk Lee, Raehyun Kim, Youngbin Park, Jaewoo Kang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Anomaly detection in an industrial process is crucial for preventing unexpected economic loss. Among various signals, multivariate time series signals are one of the most difficult signals to analyze for detecting anomalies. Moreover, labels for anomalous signals are often unavailable in many fields. To tackle this problem, we present DeepNAP which is an anomaly pre-detection model based on recurrent neural networks. Without any annotated data, DeepNAP successfully learns to detect anomalies using partial reconstruction. Furthermore, detecting anomalies in advance is essential for preventing catastrophic events. While previous studies focused mainly on capturing anomalies after they have occurred, DeepNAP is able to pre-detect anomalies. We evaluate DeepNAP and other baseline models on a real multivariate dataset generated from a semiconductor manufacturing fab. Compared with other baseline models, DeepNAP achieves the best performance on both the detection and pre-detection of anomalies.

Original languageEnglish
Pages (from-to)1-11
Number of pages11
JournalInformation Sciences
Volume457-458
DOIs
Publication statusPublished - 2018 Aug 1

Fingerprint

Anomaly
Semiconductors
Semiconductor materials
Recurrent neural networks
Labels
Time series
Baseline
Economics
Semiconductor Manufacturing
Multivariate Time Series
Anomaly Detection
Recurrent Neural Networks
Anomalous
Model-based
Partial
Evaluate
Model

Keywords

  • Anomaly detection
  • Long short term memory
  • Multivariate
  • Time series data

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this

DeepNAP : Deep neural anomaly pre-detection in a semiconductor fab. / Kim, Chunggyeom; Lee, Jinhyuk; Kim, Raehyun; Park, Youngbin; Kang, Jaewoo.

In: Information Sciences, Vol. 457-458, 01.08.2018, p. 1-11.

Research output: Contribution to journalArticle

Kim, Chunggyeom ; Lee, Jinhyuk ; Kim, Raehyun ; Park, Youngbin ; Kang, Jaewoo. / DeepNAP : Deep neural anomaly pre-detection in a semiconductor fab. In: Information Sciences. 2018 ; Vol. 457-458. pp. 1-11.
@article{bef6caf7c6c0423e9c3895f924ba42d3,
title = "DeepNAP: Deep neural anomaly pre-detection in a semiconductor fab",
abstract = "Anomaly detection in an industrial process is crucial for preventing unexpected economic loss. Among various signals, multivariate time series signals are one of the most difficult signals to analyze for detecting anomalies. Moreover, labels for anomalous signals are often unavailable in many fields. To tackle this problem, we present DeepNAP which is an anomaly pre-detection model based on recurrent neural networks. Without any annotated data, DeepNAP successfully learns to detect anomalies using partial reconstruction. Furthermore, detecting anomalies in advance is essential for preventing catastrophic events. While previous studies focused mainly on capturing anomalies after they have occurred, DeepNAP is able to pre-detect anomalies. We evaluate DeepNAP and other baseline models on a real multivariate dataset generated from a semiconductor manufacturing fab. Compared with other baseline models, DeepNAP achieves the best performance on both the detection and pre-detection of anomalies.",
keywords = "Anomaly detection, Long short term memory, Multivariate, Time series data",
author = "Chunggyeom Kim and Jinhyuk Lee and Raehyun Kim and Youngbin Park and Jaewoo Kang",
year = "2018",
month = "8",
day = "1",
doi = "10.1016/j.ins.2018.05.020",
language = "English",
volume = "457-458",
pages = "1--11",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - DeepNAP

T2 - Deep neural anomaly pre-detection in a semiconductor fab

AU - Kim, Chunggyeom

AU - Lee, Jinhyuk

AU - Kim, Raehyun

AU - Park, Youngbin

AU - Kang, Jaewoo

PY - 2018/8/1

Y1 - 2018/8/1

N2 - Anomaly detection in an industrial process is crucial for preventing unexpected economic loss. Among various signals, multivariate time series signals are one of the most difficult signals to analyze for detecting anomalies. Moreover, labels for anomalous signals are often unavailable in many fields. To tackle this problem, we present DeepNAP which is an anomaly pre-detection model based on recurrent neural networks. Without any annotated data, DeepNAP successfully learns to detect anomalies using partial reconstruction. Furthermore, detecting anomalies in advance is essential for preventing catastrophic events. While previous studies focused mainly on capturing anomalies after they have occurred, DeepNAP is able to pre-detect anomalies. We evaluate DeepNAP and other baseline models on a real multivariate dataset generated from a semiconductor manufacturing fab. Compared with other baseline models, DeepNAP achieves the best performance on both the detection and pre-detection of anomalies.

AB - Anomaly detection in an industrial process is crucial for preventing unexpected economic loss. Among various signals, multivariate time series signals are one of the most difficult signals to analyze for detecting anomalies. Moreover, labels for anomalous signals are often unavailable in many fields. To tackle this problem, we present DeepNAP which is an anomaly pre-detection model based on recurrent neural networks. Without any annotated data, DeepNAP successfully learns to detect anomalies using partial reconstruction. Furthermore, detecting anomalies in advance is essential for preventing catastrophic events. While previous studies focused mainly on capturing anomalies after they have occurred, DeepNAP is able to pre-detect anomalies. We evaluate DeepNAP and other baseline models on a real multivariate dataset generated from a semiconductor manufacturing fab. Compared with other baseline models, DeepNAP achieves the best performance on both the detection and pre-detection of anomalies.

KW - Anomaly detection

KW - Long short term memory

KW - Multivariate

KW - Time series data

UR - http://www.scopus.com/inward/record.url?scp=85047201598&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047201598&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2018.05.020

DO - 10.1016/j.ins.2018.05.020

M3 - Article

AN - SCOPUS:85047201598

VL - 457-458

SP - 1

EP - 11

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

ER -