SWS Academic Research eLibraryEarth & Planetary Sciences

Scholarly record

ANALYSIS OF AI POSSIBILITIES FOR ASSESSING EXPLOSION-PROTECTED EQUIPMENT

Marius Darie, Tiberiu Csaszar, Sorin Burian, Cosmin Colda, Danus Grecea

First published: 2025-08-15https://doi.org/10.5593/sgem2025/1.1/s06.56View metrics

Abstract

The paper presents aspects of analyzing the AI possibilities in evaluating equipment for explosive atmospheres. In the first part of the paper, the context of the use of equipment in potentially explosive atmospheres is presented. The presence of flammable substances in industrial applications leads to additional requirements for technical equipment used in such spaces. Furthermore, machinery used in such spaces must remain in working order even when the risk of explosion is present. In summary, to confirm eligibility, equipment used in such spaces must be assessed, tested, and certified to ensure it functions safely about the risk of explosion [1] and [2]. The second part sets out the testing framework considered. On this occasion, some representative tests encountered in the assessment process, applied to AI agents for the purpose of identifying the assessment performance of equipment intended [3] for use in explosive atmospheres, are presented. The types of tests considered are those in which the following is assessed: understanding a set of requirements in the standard, and assessment of the fulfillment of a set of requirements in the standard. The forms in which the information is retrieved are plain text, a picture with a calculation formula, and a picture with a drawing. The options considered are binary alternatives and multiple alternatives. In the third part, the results of the tests are presented and discussed. An important conclusion of the approach is that each AI agent exhibits an individual score in terms of performance in evaluating equipment with the type of intrinsic security protection and the ability to convey the correct information.

Publication Impact Profile

PlumX
  • Captures
  • Mendeley - Readers: 1
Dimensions ID: pub.1195348420

Publication details

Title
ANALYSIS OF AI POSSIBILITIES FOR ASSESSING EXPLOSION-PROTECTED EQUIPMENT
Authors
Marius Darie, Tiberiu Csaszar, Sorin Burian, Cosmin Colda, Danus Grecea
Proceedings
25th International Multidisciplinary Scientific GeoConference Proceedings SGEM2025, Science and Technologies in Geology, Exploration and Sustainable Mining
Publisher
STEF92 Technology
Year
2025
Pages
469-476
SWS Citekey
Darie20256469476
ISSN
1314-2704; 13142704
ISBN
9786197603798
Language
en
Publication type
Conference Paper
Proceedings contents
Open official contents
Keywords
References6
  1. ATEX Directive, Equipment for potentially explosive atmospheres (ATEX), available https://ec.europa.eu/growth/sectors/mechanical-engineering/atexen, (2014).

  2. Moldovan L., Burian S., Magyari M., Darie M., Fotau D., Factors influencing the determination of maximum surface temperature for explosion-proof luminaires, Environmental Engineering and Management Journal, Vol.16, No. 6, pp 1309-1316, 2017. DOI: 10.30638/eemj.2017.139

  3. Pasculescu V.M., Vlasin N.I., Florea D., Suvar M.C., Improving the quality of the process for selecting electrical equipment intended to be used in potentially explosive atmospheres, Quality - Access to Success, Romania, vol. 18/issue S1, pp 97-102, 2017.

  4. Government Decision no. 1058 of August 9, 2006 on the minimum requirements for improving the safety and health protection of workers who may be exposed to a potential risk due to explosive atmospheres, 2006;

  5. Standard IEC 60079-11: 2023 - Explosive atmospheres - Part 11: Equipment protection by intrinsic safety "i".

  6. SR EN (IEC) 60079-0:2018 - Explosive atmospheres - Part 0: Equipment � General requirements, ASRO, 2018;

View or Download full articleAccess options
Full paper accessChoose SWS login, librarian support, or instant article download.

SWS access login

Login as SWS Scientific Committee

Authors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.

For librarian assistance: [email protected]

Purchase Instant Access

48-hour online accessComing soon
Online-only accessComing soon
Download the full article in PDF formatEUR 35
  • Article can be downloaded after successful payment.
  • Article may be used according to SWS library access terms.
  • Article cannot be redistributed.
Get full paper

Back to publication list