A Study on Standardization of Security Evaluation Information for Chemical Processes Based on Deep Learning

Lanfei Peng,Dong Gao,Yujie Bai

doi:10.3390/pr9050832

Lanfei Peng, Dong Gao + Show 1 more

Open Access

https://doi.org/10.3390/pr9050832

Copy DOI

Journal: Processes	Publication Date: May 10, 2021
Citations: 4	License type: CC BY 4.0

Affiliation: Beijing University of Chemical Technology

Abstract

Hazard and operability analysis (HAZOP) is one of the most commonly used hazard analysis methods in the petrochemical industry. The large amount of unstructured data in HAZOP reports has generated an information explosion which has led to a pressing need for technologies that can simplify the use of this information. In order to solve the problem that massive data are difficult to reuse and share, in this study, we propose a new deep learning framework for Chinese HAZOP documents to perform a named entity recognition (NER) task, aiming at the characteristics of HAZOP documents, such as polysemy, multi-entity nesting, and long-distance text. Specifically, the preprocessed data are input into an embeddings from language models (ELMo) and a double convolutional neural network (DCNN) model to extract rich character features. Meanwhile, a bidirectional long short-term memory (BiLSTM) network is used to extract long-distance semantic information. Finally, the results are decoded by a conditional random field (CRF), and then output. Experiments were carried out using the HAZOP report of a coal seam indirect liquefaction project. The experimental results for the proposed model showed that the accuracy rate of the optimal results reached 90.83, the recall rate reached 92.46, and the F-value reached the highest 91.76%, which was significantly improved as compared with other models.

Highlights

Using the same training parameters, the convolutional neural networks (CNNs)-bidirectional long short-term memory (BiLSTM)-conditional random field (CRF) method improves the accuracy by 13.17, the recall rate by 5.40, and the F-value by 9.39
Compared with the double convolutional neural network (DCNN)-BiLSTM-CRF model, the accuracy of the embeddings from language models (ELMo)-DCNN-BiLSTM-CRF model proposed in this study is improved to 90.83, the recall rate increased to 90, and the F-value reached 91.64
In view of the fact that a large amount of text data cannot be reused in hazard analysis and operability in the petrochemical industry, in this study, a new model is proposed to perform a named entity recognition task of a Chinese hazard and operability analysis (HAZOP) document

Summary

Introduction

One of the most difficult problems in chemical plant design is identification of hazards. The industry has developed a range of hazard identification methods [1]. Compared with traditional safety analysis methods, the HAZOP method has the following three advantages: First, the concept of system security is established instead of the concept of individual device security. It is a systematic and well-integrated method, which is conducive to identifying a variety of potential hazards. Since HAZOP was first developed, it has been widely used for safety assessment and risk analyses at home and abroad [2]

Objectives

Methods

Results

Discussion

Conclusion