research-article

Open access

Online Amnestic DTW to allow Real-Time Golden Batch Monitoring

Authors:

Chin-Chia Michael Yeh,

Amirali Darvishzadeh,

Mikhail Noskov,

Eamonn KeoghAuthors Info & Claims

KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining

Pages 2604 - 2612

https://doi.org/10.1145/3292500.3330650

Published: 25 July 2019 Publication History

Abstract

In manufacturing, a golden batch is an idealized realization of the perfect process to produce the desired item, typically represented as a multidimensional time series of pressures, temperatures, flow-rates and so forth. The golden batch is sometimes produced from first-principle models, but it is typically created by recording a batch produced by the most experienced engineers on carefully cleaned and calibrated machines. In most cases, the golden batch is only used in post-mortem analysis of a product with an unexpectedly inferior quality, as plant managers attempt to understand where and when the last production attempt went wrong. In this work, we make two contributions to golden batch processing. We introduce an online algorithm that allows practitioners to understand if the process is currently deviating from the golden batch in real-time, allowing engineers to intervene and potentially save the batch. This may be done, for example, by cooling a boiler that is running unexpectedly hot. In addition, we show that our ideas can greatly expand the purview of golden batch monitoring beyond industrial manufacturing. In particular, we show that golden batch monitoring can be used for anomaly detection, attention focusing, and personalized training/skill assessment in a host of novel domains.

Supplementary Material

MP4 File (p2604-yeh.mp4)

Download
659.22 MB

References

[1]

Aspen ProMV Brochure, www.aspentech.com/en/resources/brochure/aspen-promv-brochure.

[2]

I. Assen et al., Anticipatory DTW for Efficient Similarity Search in Time Series Databases." PVLDB 2(1): 826--837 (2009).

Digital Library

[3]

O. Bau, I. Poupyrev, A. Israr, and C. Harrison. TeslaTouch: electrovibration for touch surfaces." In Proceedings of the 23nd annual ACM symposium on User interface software and technology, pp. 283--292. ACM, 2010.

Digital Library

[4]

V. Chandola, A. Banerjee, and V. Kumar. Anomaly detection: A survey." ACM computing surveys (CSUR) 41, no. 3 (2009): 15.

Digital Library

[5]

H. A. Dau et al. Optimizing dynamic time warping's window width for time series data mining applications." DMKD (2018): 1--47.

Digital Library

[6]

M. Ewerton et al. Assisting Movement Training and Execution with Visual and Haptic Feedback." Frontiers in Neurorobotics 12 (2018): 24.

[7]

M. J. Fard, S. Ameri, and R. D. Ellis. Toward Personalized Training and Skill Assessment in Robotic Minimally Invasive Surgery." In Proceedings of the World Congress on Engineering and Computer Science, vol. 2. 2016.

[8]

S. Giraldo et al. Automatic assessment of violin performance using dynamic time warping classification." In 2018 26th Signal Processing and Communications Applications Conference (SIU). IEEE, 2018.

[9]

https://musescore.com/user/7639766/scores/2847181.

[10]

F. Itakura, Minimum prediction residual principle applied to speech recognition." IEEE Transactions on Acoustics, Speech, and Signal Processing 23.1 (1975): 67--72.

[11]

P. Kah, M. Shrestha, E. Hiltunen, and J. Martikainen. Robotic arc welding sensors and programming in industrial applications." International Journal of Mechanical and Materials Engineering 10, no. 1 (2015): 13.

[12]

E. Keogh, J. Lin, and A. Fu. HOT SAX: Finding the most unusual time series subsequence: Algorithms and applications." ICDM, pp. 440--449. 2004.

Digital Library

[13]

S. Mallat. A wavelet tour of signal processing. Elsevier, 1999.

Digital Library

[14]

U. Mori, A. Mendiburu, S. Dasgupta, and J. A. Lozano. Early classification of time series by simultaneously optimizing the accuracy and earliness." IEEE Transactions on Neural Networks and Learning Systems (2017).

[15]

R. T. Olszewski. Generalized feature extraction for structural pattern recognition in time-series data. No. Carnegie Mellon University-CS-01--108, Pittsburgh, PA. 2001.

Digital Library

[16]

M. A. F. Pimentel, D. A. Clifton, L. Clifton, and L. Tarassenko. A review of novelty detection." Signal Processing 99 (2014): 215--249.

Digital Library

[17]

F. Petitjean et al. Dynamic time warping averaging of time series allows faster and more accurate classification." In ICDM, pp. 470--479. IEEE, 2014.

Digital Library

[18]

D.M.W. Powers. Evaluation: from Precision, Recall and F-measure to ROC, Informedness, Markedness and Correlation." Journal of Machine Learning Technologies, 2(1), 37--63. 2011.

[19]

Project website: https://sites.google.com/view/gbatch.

[20]

P. Qiu. Introduction to statistical process control. CRC Press, 2013.

[21]

C. Ratanamahatana and E. Keogh. Making time-series classification more accurate using learned constraints." Proceedings of the 2004 SIAM SDM.

[22]

H. Sakoe and S. Chiba. Dynamic programming algorithm optimization for spoken word recognition." IEEE transactions on acoustics, speech, and signal processing 26.1 (1978): 43--49.

[23]

D. F. Silva, G. E. A. P. A. Batista, and E. Keogh. Prefix and suffix invariant dynamic time warping." Data Mining (ICDM), 2016 IEEE 16th International Conference on. IEEE, 2016.

[24]

P. Tormene, et al. Matching incomplete time series with dynamic time warping: an algorithm and an application to post-stroke rehabilitation." Artificial intelligence in medicine 45.1 (2009): 11--34.

Digital Library

[25]

Trendminer. Video retrieved on 4/15/2018 www.trendminer.com/use-case-compare-current-batch-to-golden-batch-fingerprint/.

[26]

US Department of Health and Human Services, Food and Drug Administration. Grade A Pasteurized Milk Ordinance 2015 Revision.".

[27]

E. Wang et al. Dynamic control strategy of a distillation system for a composition-adjustable organic Rankine cycle." Energy 141 (2017).

[28]

R. Wojewodka and T. Blevins. Data Analytics in Batch Operations." Control Global. May 4, 2008. Accessed April 14, 2018. https://www.controlglobal.com/articles/2008/164/.

[29]

C.-C. M. Yeh, N. Kavantzas, and E. Keogh. Matrix profile VI: Meaningful multidimensional motif discovery." In Data Mining (ICDM), 2017 IEEE International Conference on, pp. 565--574. IEEE, 2017.

[30]

C.-C. M. Yeh et al. Time series joins, motifs, discords and shapelets: a unifying view that exploits the matrix profile." DMKD 32 (2018): 83--123.

Digital Library

[31]

Y. Zhu et al. Exploiting a novel algorithm and GPUs to break the ten quadrillion pairwise comparisons barrier for time series motifs and joins." KAIS (2018): 1--34.

Digital Library

[32]

A. Zia et al. "Video and accelerometer-based motion analysis for automated surgical skills assessment." International journal of computer assisted radiology and surgery 13, no. 3 (2018): 443--455.

Cited By

Kim SSeo HLee E(2024)Advanced Anomaly Detection in Manufacturing Processes: Leveraging Feature Value Analysis for Normalizing Anomalous DataElectronics10.3390/electronics1307138413:7(1384)Online publication date: 5-Apr-2024
https://doi.org/10.3390/electronics13071384
Zhou KQin YYuen C(2024)Graph neural network-based lithium-ion battery state of health estimation using partial discharging curveJournal of Energy Storage10.1016/j.est.2024.113502100(113502)Online publication date: Oct-2024
https://doi.org/10.1016/j.est.2024.113502
Keusch AHiessl TJoksch MSündermann ASchall DSchulte S(2023)Edge Intelligence for Detecting Deviations in Batch-based Industrial Processes2023 IEEE 21st International Conference on Industrial Informatics (INDIN)10.1109/INDIN51400.2023.10217845(1-8)Online publication date: 18-Jul-2023
https://doi.org/10.1109/INDIN51400.2023.10217845
Show More Cited By

Index Terms

Online Amnestic DTW to allow Real-Time Golden Batch Monitoring

Recommendations

Revisiting inaccuracies of time series averaging under dynamic time warping
Highlights
- Dispels misconception on correctness and drift-out phenomenon of time series averaging.
Abstract
This article revisits an analysis on (in)accuracies of time series averaging under dynamic time warping (dtw) conducted by Niennattrakul and Ratanamahatana [16]. They proposed a correctness-criterion for dtw-averages and postulated ...
Real-time product moisture content monitoring in batch dryer using psychrometric and airflow measurements

Psychrometric and airflow measurements are used to monitor a batch dryer.Algorithm retrieves sensor signals sampled by DAQ and perform calculations.Several sources of error were found to affect the method accuracy.Wet bulb temperature measurements are ...
Expert enhanced dynamic time warping based anomaly detection
Abstract
Dynamic time warping (DTW) is a well-known algorithm for time series elastic dissimilarity measure. Its ability to deal with non-linear time distortions makes it helpful in a variety of data mining tasks. Such a task is also anomaly detection ...
Highlights
- Novel anomaly detection method based on Dynamic time warping.
- The efficient representation ensures low computational and space complexity.
- Expert knowledge utilisation leads to higher detection performance on small datasets.

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining

July 2019

3305 pages

ISBN:9781450362016

DOI:10.1145/3292500

General Chairs:
Ankur Teredesai
KenSci
,
Vipin Kumar
University of Minnesota
,
Program Chairs:
Ying Li
EV Analysis Corporation
,
Rómer Rosales
LinkedIn
,
Evimaria Terzi
Boston University
,
George Karypis
University of Minnesota

Copyright © 2019 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 25 July 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

KDD '19

Sponsor:

KDD '19: The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

August 4 - 8, 2019

AK, Anchorage, USA

Acceptance Rates

KDD '19 Paper Acceptance Rate 110 of 1,200 submissions, 9%;

Overall Acceptance Rate 1,133 of 8,635 submissions, 13%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

14
Total Citations
View Citations
978
Total Downloads

Downloads (Last 12 months)102
Downloads (Last 6 weeks)8

Reflects downloads up to 16 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Kim SSeo HLee E(2024)Advanced Anomaly Detection in Manufacturing Processes: Leveraging Feature Value Analysis for Normalizing Anomalous DataElectronics10.3390/electronics1307138413:7(1384)Online publication date: 5-Apr-2024
https://doi.org/10.3390/electronics13071384
Zhou KQin YYuen C(2024)Graph neural network-based lithium-ion battery state of health estimation using partial discharging curveJournal of Energy Storage10.1016/j.est.2024.113502100(113502)Online publication date: Oct-2024
https://doi.org/10.1016/j.est.2024.113502
Keusch AHiessl TJoksch MSündermann ASchall DSchulte S(2023)Edge Intelligence for Detecting Deviations in Batch-based Industrial Processes2023 IEEE 21st International Conference on Industrial Informatics (INDIN)10.1109/INDIN51400.2023.10217845(1-8)Online publication date: 18-Jul-2023
https://doi.org/10.1109/INDIN51400.2023.10217845
Yeh CZheng YPan MChen HZhuang ZWang JWang LZhang WPhillips JKeogh E(2023)Sketching Multidimensional Time Series for Fast Discord Mining2023 IEEE International Conference on Big Data (BigData)10.1109/BigData59044.2023.10386363(443-452)Online publication date: 15-Dec-2023
https://doi.org/10.1109/BigData59044.2023.10386363
Lu YWu RMueen AZuluaga MKeogh E(2023)DAMP: accurate time series anomaly detection on trillions of datapoints and ultra-fast arriving data streamsData Mining and Knowledge Discovery10.1007/s10618-022-00911-737:2(627-669)Online publication date: 11-Jan-2023
https://doi.org/10.1007/s10618-022-00911-7
Mercer RKeogh E(2023)Novelets: a new primitive that allows online detection of emerging behaviors in time seriesKnowledge and Information Systems10.1007/s10115-023-01936-066:1(59-87)Online publication date: 10-Aug-2023
https://doi.org/10.1007/s10115-023-01936-0
Ochel JFey MBrecher C(2023)Multivariate Synchronization of NC Process Data Sets Based on Dynamic Time WarpingProduction at the Leading Edge of Technology10.1007/978-3-031-18318-8_30(288-296)Online publication date: 2-Feb-2023
https://doi.org/10.1007/978-3-031-18318-8_30
Der AYeh CWu RWang JZheng YZhuang ZWang LZhang WKeogh E(2022)Matrix Profile XXVII: A Novel Distance Measure for Comparing Long Time Series2022 IEEE International Conference on Knowledge Graph (ICKG)10.1109/ICKG55886.2022.00013(40-47)Online publication date: Nov-2022
https://doi.org/10.1109/ICKG55886.2022.00013
Mercer RKeogh E(2022)Matrix Profile XXV: Introducing Novelets: A Primitive that Allows Online Detection of Emerging Behaviors in Time Series2022 IEEE International Conference on Data Mining (ICDM)10.1109/ICDM54844.2022.00044(338-347)Online publication date: Nov-2022
https://doi.org/10.1109/ICDM54844.2022.00044
Musleh MChatzimparmpas AJusufi I(2022)Visual analysis of blow molding machine multivariate time series dataJournal of Visualization10.1007/s12650-022-00857-425:6(1329-1342)Online publication date: 11-Jul-2022
https://doi.org/10.1007/s12650-022-00857-4
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents