Detecting and locating patterns in time series using machine learning

被引：7
|
作者：
Janka, Dennis [1 ]
Lenders, Felix [1 ]
Wang, Shiyu [1 ,2 ]
Cohen, Andrew [1 ]
Li, Nuo [1 ]
机构：
[1] ABB AG, Corp Res Germany, Wallstadter Str 59, D-68526 Ladenburg, Germany
[2] Karlsruhe Inst Technol, D-76133 Karlsruhe, Germany
来源：
CONTROL ENGINEERING PRACTICE | 2019年 / 93卷
关键词：
Pattern recognition; Machine learning; Time-series classification; Industrial data analytics; Metals processing; Neural networks;
D O I：
10.1016/j.conengprac.2019.104169
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
A method is presented to detect and locate user-defined patterns in time series data. The method is based on decomposing time series into a sequence of fixed-length snapshots on which a classifier is applied. Snapshot classification results determine the exact position of the pattern. One advantage of this approach is that it can be applied to any process-specific pattern, e.g., spiking patterns, under- or overshoots, or (time-lagged) correlations. We demonstrate the efficacy of the approach by means of an example from steel production, namely a cold-rolling mill process. We detect two patterns: underswings and time-lagged spike repetition in multivariate series.
引用
收藏
页数：9
相关论文
共 50 条
  • [1] Classification of wandering patterns in the elderly using machine learning and time series analysis
    Ramos-Rivera, Daniel
    Diaz-Ramirez, Arnoldo
    Trujillo, Leonardo
    Garcia-Vazquez, Juan P.
    Mejia-Alvarez, Pedro
    IEEE LATIN AMERICA TRANSACTIONS, 2024, 22 (12) : 1009 - 1018
  • [2] Machine learning approach of detecting anomalies and forecasting time-series of IoT devices
    Malki, Amer
    Atlam, El-Sayed
    Gad, Ibrahim
    ALEXANDRIA ENGINEERING JOURNAL, 2022, 61 (11) : 8973 - 8986
  • [3] Detecting Architectural Integrity Violation Patterns Using Machine Learning
    Zakurdaeva, Alla
    Weiss, Michael
    Muegge, Steven
    PROCEEDINGS OF THE 35TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING (SAC'20), 2020, : 1480 - 1487
  • [4] Detecting Attacks and Locating Malicious Devices Using Unmanned Air Vehicles and Machine Learning
    Junior, Evilasio C.
    Costa, Wanderson L.
    Portela, Arid L. C.
    Rocha, Leonardo S.
    Domes, Rafael L.
    Andrade, Rossana M. C.
    JOURNAL OF INTERNET SERVICES AND APPLICATIONS, 2022, 13 (01) : 11 - 20
  • [5] Application of Machine Learning Methods for Recognition of Daily Patterns in Power Quality Time Series
    Strunz, Elias
    Zyabkina, Olga
    Meyer, Jan
    2022 20TH INTERNATIONAL CONFERENCE ON HARMONICS & QUALITY OF POWER (ICHQP 2022), 2022,
  • [6] Detecting Anomalous Multivariate Time-Series via Hybrid Machine Learning
    Terbuch, Anika
    O'Leary, Paul
    Khalili-Motlagh-Kasmaei, Negin
    Auer, Peter
    Zohrer, Alexander
    Winter, Vincent
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2023, 72
  • [7] Machine Learning Advances for Time Series Forecasting
    Masini, Ricardo P.
    Medeiros, Marcelo C.
    Mendes, Eduardo F.
    JOURNAL OF ECONOMIC SURVEYS, 2023, 37 (01) : 76 - 111
  • [8] Detecting satellite unknown fault patterns using digital twin and machine learning
    Shen, Yinglong
    Cai, Junliang
    Lin, Jiawei
    Yang, Fan
    CHINESE SPACE SCIENCE AND TECHNOLOGY, 2025, 45 (01) : 46 - 58
  • [9] Combining Machine Learning and Symbolic Representation of Time Series for Classification of Behavioural Patterns
    Carballo Perez, Paula
    Ortega, Felipe
    Navarro Garcia, Jorge
    Martin de Diego, Isaac
    ICSLT 2019: PROCEEDINGS OF THE 5TH INTERNATIONAL CONFERENCE ON E-SOCIETY, E-LEARNING AND E-TECHNOLOGIES, 2019, : 93 - 97
  • [10] Time Series Analysis on Earthquakes Using EDA and Machine Learning
    Azis, Muhammad Fakhrillah Abdul
    Darari, Fariz
    Septyandy, Muhammad Rizqy
    ICACSIS 2020: 2020 12TH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTER SCIENCE AND INFORMATION SYSTEMS (ICACSIS), 2020, : 405 - 411
12345