A Study on the Diagnostics Method for Plant Equipment Failure - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2019

A Study on the Diagnostics Method for Plant Equipment Failure

Minyoung Seo
  • Function : Author
  • PersonId : 1061587
Hong-Bae Jun
  • Function : Author
  • PersonId : 1050382


Recently, in the era of the Fourth Industrial Revolution, the rapid development of ICT (Information and Communication Technology) and IoT (Internet of Things) technology have been actively applied to collect and utilize the status data of plant equipment during their operation period. With these technologies it is very important to keep the availability and reliability of the equipment during its usage period without any interruption or failure. In this vein, the CBM (Condition Based Maintenance) or PHM (Prognostics and Health Management) policy which carries out maintenance activities based on the condition of the equipment has been increasingly applied to the plant industry. Although it has a high potential to derive the important value from operation data of plant equipment through data analytics, research on data analytics in the plant industry is still known as an early stage. In this study, we briefly introduce a method to diagnose the fault state of the equipment by detecting patterns related to the failure modes of equipment based on gathered sensor data. To develop the method, we apply the well-known clustering/classification algorithms and text mining and information retrieval method. In a case study, we apply the proposed method and show its possibility throughout preliminary experiments.
Fichier principal
Vignette du fichier
489100_1_En_85_Chapter.pdf (91.39 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02419258 , version 1 (19-12-2019)





Minyoung Seo, Hong-Bae Jun. A Study on the Diagnostics Method for Plant Equipment Failure. IFIP International Conference on Advances in Production Management Systems (APMS), Sep 2019, Austin, TX, United States. pp.701-707, ⟨10.1007/978-3-030-30000-5_85⟩. ⟨hal-02419258⟩
49 View
18 Download



Gmail Facebook Twitter LinkedIn More