Prevention and control strategy of coal mine water inrush accident based on case-driven and Bow-Tie-Bayesian model

Energy, Год журнала: 2025, Номер unknown, С. 135312 - 135312

Опубликована: Фев. 1, 2025

Язык: Английский

---

Chemical process safety domain knowledge graph‐enhanced LLM for efficient emergency response decision support

The Canadian Journal of Chemical Engineering, Год журнала: 2025, Номер unknown

Опубликована: Апрель 24, 2025

Abstract Chemical process safety accidents are characterized by their sudden onset, rapid evolution, and severe consequences. Developing effective emergency response decisions for such complex dynamic incidents requires comprehensively considering various knowledge domains. Relying solely on expert experience plans often fails to meet the demands of response. To enhance efficiency decision‐making in chemical accidents, this study proposes a method that leverages graph (CPSKG) large language models (LLMs) generating reliable decisions. The proposed uses seven‐step approach designing scenario ontologies. By aligning with characteristics domain texts ontology framework, natural processing (NLP) retrieval‐augmented generation using graphs (Graph RAG) techniques employed construct semantically rich CPSKG. entities relationships within reasoning capabilities LLMs, facilitating efficient A case was conducted validate reliability approach. results demonstrate LLM enhanced CPSKG outperforms other more As key contribution, improves sharing while auxiliary

Язык: Английский

---

STheBaN - System-Theoretic Bayesian approach for the evaluation of inspections workability in hydrogen operations

Journal of Loss Prevention in the Process Industries, Год журнала: 2025, Номер unknown, С. 105687 - 105687

Опубликована: Май 1, 2025

Язык: Английский

---

Physics-informed data-driven Bayesian network for the risk analysis of hydrogen refueling stations

International Journal of Hydrogen Energy, Год журнала: 2024, Номер 110, С. 371 - 385

Опубликована: Март 1, 2024

Язык: Английский

---