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

Valcamonico, Dario; Baraldi, Piero; Zio, Enrico

doi:10.1109/icsrs53853.2021.9660733

Cited by 3 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the occurrence of a PSE, system operators write a textual report with free-text and multiplechoice fields to describe the event, its causes and consequences, and the level of severity of the LOPC with reference to predefined tier levels ("API RP 754" 2021). A methodological framework based on the combination of techniques of Natural Language Processing (NLP) and a Bayesian Network (BN) has been proposed for the systematic analysis of PSE reports in (Valcamonico et al 2022). The present work consolidates and extends the previous work (Valcamonico et al 2022) with the final aim of periodically estimating the performance of the safety barriers.…”

Section: Introductionmentioning

confidence: 75%

“…A methodological framework based on the combination of techniques of Natural Language Processing (NLP) and a Bayesian Network (BN) has been proposed for the systematic analysis of PSE reports in (Valcamonico et al 2022). The present work consolidates and extends the previous work (Valcamonico et al 2022) with the final aim of periodically estimating the performance of the safety barriers.…”

Section: Introductionmentioning

confidence: 75%

“…The method proposed for the identification of the keywords of the PSE reports extends the method proposed in (Valcamonico et al 2022) for the same purpose. The main difference is that the new method considers the time of occurrence of the PSEs.…”

Section: Abstract Identificationmentioning

confidence: 97%

“…n-grams, used in the set of reports . Then, the identification of the ngrams is obtained by computing their Normalized Pointwise Mutual Information (NPMI) index (Bouma 2009), which measures the amount of information that a specific n-gram carries with respect to the information of the words alone, and by including it in only if its associated NPMI index is larger than a threshold set using the procedure described in (Valcamonico et al 2023).…”

Section: Abstract Identificationmentioning

confidence: 99%

“…The taxonomy of the words associated with the design, operation and failure of the safety barriers is built by experts of the hydrocarbon production assets and used to organize the words into a topdown structure of sub-levels, where each sublevel represents a specific safety barrier (Mackie, Welsh, and Lee 2006). Then, the methodology developed in (Valcamonico et al 2022) to identify the keywords associated to the reports, which is based on the NLP technique of Term Frequency Inverse Document Frequency (TFIDF) (Weiss et al 2005), is modified to account for possible modifications of the asset. The idea, inspired by (Marwah and Beel 2020), is to multiply the TFIDF of a word in a report by an additional term inversely proportional to the age of the report, so that words written in recent PSEs are more important than words written in old PSEs.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Method based on Natural Language Processing for Periodically Estimating Variations of Performance of Safety Barriers in Hydrocarbon Production Assets

Valcamonico,

Baraldi,

Zio

et al. 2023

Proceeding of the 33rd European Safety and Reliability Conference

View full text Add to dashboard Cite

This work develops a methodology for estimating the performance of safety barriers of hydrocarbon production assets using reports of Process Safety Events (PSEs). We address the challenge of dealing with assets that evolve, e.g., due to degradation of components or maintenance interventions, so that also the performances of the safety barriers vary in time. The proposed methodology combines a taxonomy of the words used in the reports, a method of Natural Language Processing (NLP) for the extraction of the keywords, which takes into account the time of occurrence of the PSEs, and a technique for estimating the barrier performance from the number and severity of PSEs involving the barrier. The proposed methodology is validated using a repository of reports of PSEs in hydrocarbon production plants.

show abstract

Section: Introductionmentioning

confidence: 75%

Section: Introductionmentioning

confidence: 75%

Section: Abstract Identificationmentioning

confidence: 97%

Section: Abstract Identificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Method based on Natural Language Processing for Periodically Estimating Variations of Performance of Safety Barriers in Hydrocarbon Production Assets

Valcamonico,

Baraldi,

Zio

et al. 2023

Proceeding of the 33rd European Safety and Reliability Conference

View full text Add to dashboard Cite

show abstract

A Scoping Literature Review of Natural Language Processing Application to Safety Occurrence Reports

Ricketts

Barry

Guo

et al. 2023

Safety

View full text Add to dashboard Cite

Safety occurrence reports can contain valuable information on how incidents occur, revealing knowledge that can assist safety practitioners. This paper presents and discusses a literature review exploring how Natural Language Processing (NLP) has been applied to occurrence reports within safety-critical industries, informing further research on the topic and highlighting common challenges. Some of the uses of NLP include the ability for occurrence reports to be automatically classified against categories, and entities such as causes and consequences to be extracted from the text as well as the semantic searching of occurrence databases. The review revealed that machine learning models form the dominant method when applying NLP, although rule-based algorithms still provide a viable option for some entity extraction tasks. Recent advances in deep learning models such as Bidirectional Transformers for Language Understanding are now achieving a high accuracy while eliminating the need to substantially pre-process text. The construction of safety-themed datasets would be of benefit for the application of NLP to occurrence reporting, as this would allow the fine-tuning of current language models to safety tasks. An interesting approach is the use of topic modelling, which represents a shift away from the prescriptive classification taxonomies, splitting data into “topics”. Where many papers focus on the computational accuracy of models, they would also benefit from real-world trials to further inform usefulness. It is anticipated that NLP will soon become a mainstream tool used by safety practitioners to efficiently process and gain knowledge from safety-related text.

show abstract

A Taxonomy for Modelling Reports of Process Safety Events in the Oil and Gas Industry

Valcamonico¹,

Baraldi²,

Zio³

et al. 2022

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

View full text Add to dashboard Cite

The Process Safety Management System (PSMS) of an industrial asset relies on multiple and independent barriers for preventing the occurrence of major accidents and/or mitigating their consequences on people, environment, asset and company reputation. It is, then, fundamental to assess the performance of the barriers with respect to the occurrence of Process Safety Events (PSEs), i.e. unplanned or uncontrolled events during which a Loss Of Primary Containment (LOPC) of any material, including non-toxic and non-flammable material, occurs. An essential aspect of PSMS is learning from incidents and taking corrective actions to prevent their recurrence. For this, a procedure for timely and consistently reporting and investigating PSEs is generally implemented. After the occurrence of a PSE, a report containing free-text and multiple-choice fields is filed to describe the PSE, its causes and consequences, and to provide a quantification of its the level of severity with reference to predefined Tier levels, as per API RP 754 guidelines. This work investigates the possibility of text-mining and structuring the knowledge on the performance of the PSMS from an electronic repository of PSE reports. The methodology developed falls within the framework of Natural Language Processing (NLP), combining Term Frequency Inverse Document Frequency (TFIDF) and Normalized Pointwise Mutual Information (NPMI) for the automatic extraction of keywords from the PSE reports. Then, a taxonomy is built to organize the vocabulary in a top-down structure of homogeneous categories, such that semantic and functional relations between and within them can be defined. Based on these relations, a Bayesian Network (BN) is developed for modeling the PSEs consequences. The proposed methodology is applied to a repository of real reports concerning the PSEs of hydrocarbon facilities of an Oil and Gas (O&G) company.

show abstract

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

Cited by 3 publications

References 8 publications

A Method based on Natural Language Processing for Periodically Estimating Variations of Performance of Safety Barriers in Hydrocarbon Production Assets

A Method based on Natural Language Processing for Periodically Estimating Variations of Performance of Safety Barriers in Hydrocarbon Production Assets

A Scoping Literature Review of Natural Language Processing Application to Safety Occurrence Reports

A Taxonomy for Modelling Reports of Process Safety Events in the Oil and Gas Industry

Contact Info

Product

Resources

About