LSTM-Autoencoder for Vibration Anomaly Detection in Vertical Carousel Storage and Retrieval System (VCSRS).

Advanced Search

Jae Seok Do, Akeem Bayo Kareem, Jang-Wook Hur

Author Information

Jae Seok Do: Department of Mechanical Engineering (Department of Aeronautics, Mechanical and Electronic Convergence Engineering), Kumoh National Institute of Technology, 61 Daehak-ro, Gumi-si 39177, Gyeonsang-buk-do, Republic of Korea.
Akeem Bayo Kareem: Department of Mechanical Engineering (Department of Aeronautics, Mechanical and Electronic Convergence Engineering), Kumoh National Institute of Technology, 61 Daehak-ro, Gumi-si 39177, Gyeonsang-buk-do, Republic of Korea. ORCID
Jang-Wook Hur: Department of Mechanical Engineering (Department of Aeronautics, Mechanical and Electronic Convergence Engineering), Kumoh National Institute of Technology, 61 Daehak-ro, Gumi-si 39177, Gyeonsang-buk-do, Republic of Korea.

PMID: 36679806 DOI: 10.3390/s23021009

Industry 5.0, also known as the "smart factory", is an evolution of manufacturing technology that utilizes advanced data analytics and machine learning techniques to optimize production processes. One key aspect of Industry 5.0 is using vibration data to monitor and detect anomalies in machinery and equipment. In the case of a vertical carousel storage and retrieval system (VCSRS), vibration data can be collected and analyzed to identify potential issues with the system's operation. A correlation coefficient model was used to detect anomalies accurately in the vertical carousel system to ascertain the optimal sensor placement position. This model utilized the Fisher information matrix (FIM) and effective independence (EFI) methods to optimize the sensor placement for maximum accuracy and reliability. An LSTM-autoencoder (long short-term memory) model was used for training and testing further to enhance the accuracy of the anomaly detection process. This machine-learning technique allowed for detecting patterns and trends in the vibration data that may not have been evident using traditional methods. The combination of the correlation coefficient model and the LSTM-autoencoder resulted in an accuracy rate of 97.70% for detecting anomalies in the vertical carousel system.

anomaly detection autoencoder automatic storage and retrieval system deep learning long short-term memory signal processing vibration sensors

Sensors (Basel). 2021 Sep 07;21(18): [PMID: 34577203]

Sci Rep. 2021 Oct 4;11(1):19638 [PMID: 34608186]

Sensors (Basel). 2022 Feb 05;22(3): [PMID: 35161952]

Sensors (Basel). 2021 Nov 08;21(21): [PMID: 34770731]

Sensors (Basel). 2019 Jul 04;19(13): [PMID: 31277390]

Sensors (Basel). 2021 Jan 26;21(3): [PMID: 33530476]

Sensors (Basel). 2020 Oct 02;20(19): [PMID: 33023175]

Sensors (Basel). 2019 Oct 23;19(21): [PMID: 31652821]

Sensors (Basel). 2020 Nov 04;20(21): [PMID: 33158213]

Sensors (Basel). 2021 Jun 23;21(13): [PMID: 34201798]

Comput Intell Neurosci. 2022 Mar 16;2022:1945507 [PMID: 35341162]

Sensors (Basel). 2021 Dec 13;21(24): [PMID: 34960414]

Sci Rep. 2021 Sep 21;11(1):18757 [PMID: 34548504]

Scientometrics. 2022;127(6):3117-3144 [PMID: 35502439]

J Cloud Comput (Heidelb). 2022;11(1):40 [PMID: 36101900]

Sensors (Basel). 2021 Oct 08;21(19): [PMID: 34640997]

Med Image Anal. 2021 Jul;71:102048 [PMID: 33872961]

Sci Rep. 2019 Dec 13;9(1):19038 [PMID: 31836728]

Sensors (Basel). 2022 Jan 13;22(2): [PMID: 35062554]

Sensors (Basel). 2022 Apr 20;22(9): [PMID: 35590855]

Sensors (Basel). 2022 Oct 26;22(21): [PMID: 36365909]

Multidimens Syst Signal Process. 2012 Sep;23(3):349-379 [PMID: 23049166]

Sensors (Basel). 2020 Oct 20;20(20): [PMID: 33092213]

(IITP--2020--2020--0--01612)/This research was supported by the MSIT~(Ministry of Science and ICT), Korea, under the Grand Information Technology Research Center support program (IITP--2020--2020--0--01612) supervised by the IITP~(Institute for Information and communications Technolo

Reproducibility of Results

Vibration

Physical Therapy Modalities

Commerce

Data Science

Journal Article

OpenLB
Open Library of Bioscience