Yes, DLGM! A novel hierarchical model for hazard classification

TL;DR

This paper introduces DLGM, a hierarchical deep learning model that combines BERT, grey modeling, and neural networks for hazard classification from textual hazard descriptions, enhancing industrial safety decision-making.

Contribution

The paper presents a novel hierarchical hazard classification model integrating BERT, grey modeling, and neural networks, addressing a previously unexplored research area.

Findings

DLGM effectively classifies hazards with promising accuracy.

FSGM(1,1) and HFFNN are proven effective components.

Experimental results demonstrate the model's practical applicability.

Abstract

Hazards can be exposed by HAZOP as text information, and studying their classification is of great significance to the development of industrial informatics, which is conducive to safety early warning, decision support, policy evaluation, etc. However, there is no research on this important field at present. In this paper, we propose a novel model termed DLGM via deep learning for hazard classification. Specifically, first, we leverage BERT to vectorize the hazard and treat it as a type of time series (HTS). Secondly, we build a grey model FSGM(1, 1) to model it, and get the grey guidance in the sense of the structural parameters. Finally, we design a hierarchical-feature fusion neural network (HFFNN) to investigate the HTS with grey guidance (HTSGG) from three themes, where, HFFNN is a hierarchical structure with four types of modules: two feature encoders, a gating mechanism, and a deepening mechanism. We take 18 industrial processes as application cases and launch a series of experiments. The experimental results prove that DLGM has promising aptitudes for hazard classification and that FSGM(1, 1) and HFFNN are effective. We hope our research can contribute added value and support to the daily practice in industrial safety.