EUVIMEDEUVIMED entdecken
Crossref

Implementation of an AI‐Based Expert System for Functional Safety of Machinery

Padma Iyenghar

Risk Analysis · 2025

DOI: 10.1111/risa.70151 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Risk Analysis, 2025. Verfasst von Padma Iyenghar. Beteiligte Einrichtung: innotec GmbH-TÜV Austria Group, Filderstadt, Germany. Hauptthemen laut MEDLINE: Expert Systems, Safety, Artificial Intelligence. Die Arbeit nennt 55 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents the design and implementation of an expert system for the domain of functional safety of machinery, featuring a novel multilingual chatbot interface developed using the Rasa framework. Unlike traditional expert systems, this approach aims to make the complex topic of functional safety more accessible to users with limited experience by assisting with tasks such as hazard identification, risk assessment, risk reduction, and safety function recommendation. The knowledge base of the system can be populated by functional safety experts through a graphical user interface, ensuring the system's utility and accuracy. This work demonstrates that the chatbot‐based expert system retains many advantages of traditional expert systems while offering a more engaging user experience. An experimental evaluation of the presented expert system using hazard scenarios from real‐life projects highlights the benefits of advanced machine learning techniques and pretrained embeddings, showing improvements in system performance. Continuous updates to the training dataset are essential for maintaining effectiveness in diverse environments. Compared to general‐purpose chatbots like ChatGPT, this system provides reliable, standards‐based insights. The system can be utilized by inexperienced machinery design personnel, such as mechanical and mechatronic engineers, before consulting with safety experts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Expert SystemsSafetyArtificial IntelligenceRisk AssessmentHumansMachine LearningUser-Computer Interface

Stichwörter der Autor:innen

ISO 12100ISO 13849artificial intelligence (AI)chatbotexpert systemfunctional safetyhazard identificationmachineryrisk assessmentrisk reduction

Autor:innen und Institutionen

  • innotec GmbH-TÜV Austria Group, Filderstadt, Germany.

Zitieren

APA

Iyenghar, P. (2025). Implementation of an AI‐Based Expert System for Functional Safety of Machinery. Risk Analysis. https://doi.org/10.1111/risa.70151

Vancouver

Iyenghar P. Implementation of an AI‐Based Expert System for Functional Safety of Machinery. Risk Analysis. 2025. doi:10.1111/risa.70151

BibTeX
@article{Iyenghar2025,
  author = {Iyenghar, Padma},
  title = {Implementation of an AI‐Based Expert System for Functional Safety of Machinery},
  journal = {Risk Analysis},
  year = {2025},
  doi = {10.1111/risa.70151}
}
Kostenlos starten →