A Novel Knowledge Graph Development for Industry Design: A Case Study on Indirect Coal Liquefaction Process

This paper develops an Industrial Safety Knowledge Graph (ISKG) from HAZOP reports using deep learning-based information extraction combined with a novel ISK standardization framework. The methodology bridges data science and engineering design, enabling knowledge reuse across different process contexts. For MOC, this work is highly relevant because it addresses one of the biggest challenges in change management: ensuring that accumulated safety knowledge from previous hazard analyses is accessible and queryable when reviewing new changes. Rather than reviewing each MOC from scratch, engineers could query the ISKG to identify similar past changes, their associated hazards, and implemented safeguards—dramatically improving the efficiency and thoroughness of MOC reviews.