A Text Mining and NLP Approach for Identifying Potential Consequences of Accidents in an Oil Refinery

Macêdo, July Bias; Aichele, Diego; Moura, Márcio das Chagas; Lins, Isis Didier

doi:10.3850/978-981-14-8593-0_4527-cd

Cited by 3 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, Macêdo and Maior had tested the NL-state-of-art method named “Bidirectional Encoder Representations from Transformers” (BERT) in their study ( 53 , 54 ). Maior et al focused on predicting the injury leave taken based on the occupational accident at a hydropower company and Macêdo used to identify the potential consequences of occupational accidents in the oil refinery industry.…”

Section: Resultsmentioning

confidence: 99%

“…As these techniques are useful in prediction analysis, several types of research were conducted to predict the occupational injury ( 44 , 52 ) and severity of the occupational injury ( 39 ). Moreover, the potential consequences of the occupational injury, as well as, the outcomes of the occupational injury were also predicted ( 19 , 24 , 37 , 53 ).…”

Section: Resultsmentioning

confidence: 99%

“…Thus, much attention is given to the construction industry. However, other industries are also present which are mining ( 19 , 32 ), steel ( 39 , 52 ), hydropower ( 54 ), oil and gas ( 37 , 53 ), electricity ( 47 , 51 ), and chemical plant ( 29 ). It was proven that the analysis of occupational injury reports is expanding across sectors.…”

Section: Discussionmentioning

confidence: 99%

“…About the databases gathered in the studies, some of the narratives are publicly accessed such as the “Occupational Safety and Health Administration (OSHA)” ( 27 , 33 – 35 , 44 , 45 ), “Mine Safety and Health Administration” ( 19 , 32 ), and “Survey of Occupational Injury and Illness” ( 40 ), beside the databases from the relevant government agencies ( 25 , 26 , 28 ). However, most of the studies represent the internal databases from the respective sector and industry, mainly the occupational injury reports including the records from preliminary hazard analysis ( 53 ) and worker's compensation claims ( 38 , 41 , 50 ). In a recent study ( 28 ), the data is gathered and analyzed from various sources which were including the published information by the authorities, published papers, and books.…”

Section: Discussionmentioning

confidence: 99%

“…Researchers may explore the analysis of more occupational injury characteristics, for example, the “activity-based factor,” “causal-and-effect relationship,” and “factor-and-severity relationship” to reveal more mechanisms contributed to workplace injury ( 28 , 40 , 68 ). Additionally, the documents on engineering and technical aspects, as well as, the environmental factors are encouraged to be incorporated in producing comprehensive information for results improvement ( 26 , 53 ).…”

Section: Discussionmentioning

confidence: 99%

See 4 more Smart Citations

Predicting occupational injury causal factors using text-based analytics: A systematic review

Khairuddin

Hasikin‬

Razak

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

Workplace accidents can cause a catastrophic loss to the company including human injuries and fatalities. Occupational injury reports may provide a detailed description of how the incidents occurred. Thus, the narrative is a useful information to extract, classify and analyze occupational injury. This study provides a systematic review of text mining and Natural Language Processing (NLP) applications to extract text narratives from occupational injury reports. A systematic search was conducted through multiple databases including Scopus, PubMed, and Science Direct. Only original studies that examined the application of machine and deep learningbased Natural Language Processing models for occupational injury analysis were incorporated in this study. A total of , out of articles were reviewed in this study by adopting the Preferred Reporting Items for Systematic Review (PRISMA). This review highlighted that various machine and deep learning-based NLP models such as K-means, Naïve Bayes, Support Vector Machine, Decision Tree, and K-Nearest Neighbors were applied to predict occupational injury. On top of these models, deep neural networks are also included in classifying the type of accidents and identifying the causal factors. However, there is a paucity in using the deep learning models in extracting the occupational injury reports. This is due to these techniques are pretty much very recent and making inroads into decision-making in occupational safety and health as a whole. Despite that, this paper believed that there is a huge and promising potential to explore the application of NLP and text-based analytics in this occupational injury research field. Therefore, the improvement of data balancing techniques and the development of an automated decision-making

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Predicting occupational injury causal factors using text-based analytics: A systematic review

Khairuddin

Hasikin‬

Razak

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

show abstract

Natural Language Processing and Bayesian Networks for the Analysis of Process Safety Events

Valcamonico

Baraldi

Zio

2021

2021 5th International Conference on System Reliability and Safety (ICSRS)

View full text Add to dashboard Cite

Identification of Features of Rare Risk Events in Oil Refineries Using Natural Language Processing (NLP)

Macêdoa,

Moura,

Lins

et al. 2022

Book of Extended Abstracts for the 32nd European Safety and Reliability Conference

View full text Add to dashboard Cite

Accidents in the process industry can be prevented and their consequences mitigated by performing proper risk analyses to inform decision making. Quantitative risk analysis (QRA) is one of the main frameworks used for risk assessment and the identification of all hazards, which a plant is exposed to. There are crucial tasks to ensure the comprehensiveness of QRA that are carried out by the examination of a set of engineering documents by experts during structured meetings. The hazards identified are stored as textual data in documents, which retain valuable information about the risks related to the analyzed system. In this context, Natural Language Processing (NLP) techniques have emerged as a way for extracting, organizing and classifying relevant information from text. However, a challenge arises when we are interested in addressing catastrophic accidents that are rare and for which, thus, only limited information is available. Some accidents are actually postulated as possible in principle, but there are no historical occurrence records. Developing techniques to characterize features about such rare events is a challenging task, yet quite useful for QRA, whose outcomes would guide designing preventive measures and supporting decision making. In this paper, we applied data augmentation (DA) and investigate different configurations to address the rare event issue. DA is applied to obtain a balanced and sufficiently large training set. The final aim of this work is developing a model capable of characterizing relevant features about rare or unseen accidental scenarios in support to hazard and operability study (HAZOP) and preliminary hazard analysis (PrHA).

show abstract

A Text Mining and NLP Approach for Identifying Potential Consequences of Accidents in an Oil Refinery

Cited by 3 publications

References 0 publications

Predicting occupational injury causal factors using text-based analytics: A systematic review

Predicting occupational injury causal factors using text-based analytics: A systematic review

Natural Language Processing and Bayesian Networks for the Analysis of Process Safety Events

Identification of Features of Rare Risk Events in Oil Refineries Using Natural Language Processing (NLP)

Contact Info

Product

Resources

About