• Title/Summary/Keyword: fault detection

Search Result 1,632, Processing Time 0.023 seconds

A Study on the Development of integrated Process Safety Management System based on Artificial Intelligence (AI) (인공지능(AI) 기반 통합 공정안전관리 시스템 개발에 관한 연구)

  • KyungHyun Lee;RackJune Baek;WooSu Kim;HeeJeong Choi
    • The Journal of the Convergence on Culture Technology
    • /
    • v.10 no.1
    • /
    • pp.403-409
    • /
    • 2024
  • In this paper, the guidelines for the design of an Artificial Intelligence(AI) based Integrated Process Safety Management(PSM) system to enhance workplace safety using data from process safety reports submitted by hazardous and risky facility operators in accordance with the Occupational Safety and Health Act is proposed. The system composed of the proposed guidelines is to be implemented separately by individual facility operators and specialized process safety management agencies for single or multiple workplaces. It is structured with key components and stages, including data collection and preprocessing, expansion and segmentation, labeling, and the construction of training datasets. It enables the collection of process operation data and change approval data from various processes, allowing potential fault prediction and maintenance planning through the analysis of all data generated in workplace operations, thereby supporting decision-making during process operation. Moreover, it offers utility and effectiveness in time and cost savings, detection and prediction of various risk factors, including human errors, and continuous model improvement through the use of accurate and reliable training data and specialized datasets. Through this approach, it becomes possible to enhance workplace safety and prevent accidents.

Two-Dimensional Interpretation of Ear-Remote Reference Magnetotelluric Data for Geothermal Application (심부 지열자원 개발을 위한 원거리 기준점 MT 탐사자료의 2차원 역산 해석)

  • Lee, Tae-Jong;Song, Yoon-Ho;Uchida, Toshihiro
    • Geophysics and Geophysical Exploration
    • /
    • v.8 no.2
    • /
    • pp.145-155
    • /
    • 2005
  • A two-dimensional (2-D) interpretation of MT data has been performed for the purpose of fracture detection for geothermal development. Remote stations have been operated in Kyushu, Japan (480 km apart) as well as in Korea (60 km and 165 km apart in 2002 and 2003 data set, respectively). Apparent resistivity and phase curves calculated by remote processing with the Japan remote data showed enough quality for 2-D inversion for the whole frequency range. Remote reference processing with Korea remote reference data also showed quite good continuity in apparent resistivity and phase curves except some noisy frequency bands; around the power frequency, 60 Hz, and around the dead band $10^{-1}Hz\;Hz\;\~1\;Hz$, where the natural EM signal is known to be very weak. Even though the subsurface showed severe three-dimensional (3-D) characteristics in the survey area so that 2-D inversion by itself could not give enough information for deep geological structures, the 2-D inversion for the 5 survey lines showed several common features. The conductive semi-consolidate mudstone layer is dipping from north to south (about 500 m depth on the south and 200 m on the north most part of the survey area). The boundary between the low (L-2) and high (H-2) resistivity anomalies can be thought as a major fault with strike $N15^{\circ}E$, passing through the sites 206, 112 and 414. The shallow (< 1 km) conductive anomalies (L-4) seem to be fracture zones having strike E-W (at site 105) and $N60^{\circ}W$ (at site 434). And there exists a conductive layer in the western and west-southern part of the survey area in the depth below $2\~3\;km$, for which further investigation is to be needed.