How harsh work environments affect the occupational accident phenomenology? Risk assessment and decision making optimisation

Murè, Salvina; Comberti, Lorenzo; Demichela, Micaela

doi:10.1016/j.ssci.2017.01.004

Cited by 20 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Damage analysis relies on the area classification result (represented as the ID index which can be determined with Table 10 and other factors summarized in Table 10: personnel presence (PL), dust explosion index (KST), gas explosion index (KG), cloud volume (VZ), layer thickness (SS), confined dust cloud (CN), as detailed in References [4,5] and summarized in Table 11. The semi-quantitative parameter, D HOF , can be then calculated according to Equations…”

Section: Damage Analysismentioning

confidence: 99%

“…The risk assessment methodology is used for risk-based decision making in process plants as the hazard identification techniques, such as HazOp and fault tree analysis [2][3][4], or even the decision analysis [5][6][7], are not used for the purpose of ATEX because they are too complex and detailed. For this reason, different ATEX risk assessment methodologies were developed to fulfil the directive requirements.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ATEX-HOF Methodology: Innovation Driven by Human and Organizational Factors (HOF) in Explosive Atmosphere Risk Assessment

Geng

Murè²,

Demichela

et al. 2020

Safety

Self Cite

View full text Add to dashboard Cite

ATEX (explosive atmosphere) risk assessment is required when any equipment or system could generate a potentially explosive atmosphere. Despite the fact that many operations on plants and equipment containing dangerous substances are performed by operators, influences of human and organizational factors (HOF) are mostly neglected in the ATEX risk assessment. The integrated methodology described here is proposed to address two challenges: (1) identification of the HOF influence on the ATEX risk assessment, and (2) quantification of the HOF influence. The proposed methodology enriches the traditional ATEX risk assessment procedure, which consists of four steps: (1) area classification, (2) ignition source identification, (3) damage analysis, and (4) ATEX risk evaluation. The advantages of the ATEX-HOF methodology are demonstrated through the application to a paint mixing station in an automotive manufacturing plant. The ATEX risk assessment methodologies are mainly semi-quantitative. The ATEX-HOF methodology provides a quantitative analysis for the area classification and ignition source identification, and a semi-quantitative approach for the damage analysis. As a result, the ATEX-HOF risk evaluation becomes more accurate. An event tree-based probabilistic assessment has been introduced, considering both the technical barrier failure (Prtbf) and the human intervention in terms of human error probability (HEP). The case study allowed for demonstrating how taking HOFs into account is particularly important in companies where the safety culture is lower and consequently, the usual hypothesis of the correctness of operator intervention (in maintenance, normal operations, and emergency) could bring to non-conservative results.

show abstract

Section: Damage Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

ATEX-HOF Methodology: Innovation Driven by Human and Organizational Factors (HOF) in Explosive Atmosphere Risk Assessment

Geng

Murè²,

Demichela

et al. 2020

Safety

Self Cite

View full text Add to dashboard Cite

show abstract

“…A specific example is provided by Li and Chen [46] who demonstrate how a commercial bank solves the same problem through a combination of a logical regression algorithm and a neural network. A hybrid approach combining methods using neural networks and fuzzy logic is provided by Muré, Combeerti, and Demichela [47]. Another hybrid model that combines time series feature extraction and a deep neural network is used by Zhao, Fan, and Zhai [48] to evaluate and predict traffic development.…”

Section: Company Specific Modelmentioning

confidence: 99%

Creating a Comprehensive Method for the Evaluation of a Company

et al. 2020

View full text Add to dashboard Cite

For investment purposes, the evaluation of a company is not only a matter for a company itself, but also for shareholders and external persons. There are many methods for evaluating a company. This contribution therefore focuses on the creation of a comprehensive method for the evaluation of an industrial enterprise, one that can be used to predict potential future bankruptcies, using a dataset of financial statements of active companies and those in liquidation in the period 2015–2019. Artificial neural networks were used to process the data, specifically logistic regressions from the data processed in the Statistica and Mathematica software programmes. The results showed that the models created using the Mathematica software are not applicable in practice due to the parameters of the obtained results. In contrast, the artificial neural structures obtained using the neural network model in the Statistica software were prospective due to their performance, which is almost always above 0.8, and the logical economic interpretation of the relevant variables. All the generated and retained networks show excellent performance and few errors. However, one of the artificial structures, network no. 4 (MLP 16-16-2), produces better results than the others. Overall, accuracy is almost 81%. In the case of the classification of companies capable of surviving financial distress, accuracy is almost 90%, with that for the classification of companies at risk of going into bankruptcy at nearly 55%.

show abstract

“…As a part of unsupervised learning, clustering [23] is the process of grouping data sets that are more similar to each other. Risk analysis [24] and Market segmentation [25] processes have been performed by researchers and organizations using the method of clustering. However, not many studies have been directed to examine whether independent clustering algorithms can be applied to predict equipment reliability.…”

Section: Literature Reviewmentioning

confidence: 99%

Using Machine Learning Algorithms on data residing in SAP ERP Application to predict equipment failures

Kohli¹

2018

IJET

View full text Add to dashboard Cite

Asset intensive Organizations have searched long for a framework model that would timely predict equipment failure. Timely prediction of equipment failure substantially reduces direct and indirect costs, unexpected equipment shut-downs, accidents, and unwarranted emission risk. In this paper, the author proposes a model that can predict equipment failure by using data from SAP Plant Maintenance module. To achieve that author has applied data extraction algorithm and numerous data manipulations to prepare a classification data model consisting of maintenance records parameters such as spare parts usage, time elapsed since last completed maintenance and the period to the next scheduled maintained and so on. By using unsupervised learning technique of clustering, the author observed a class to cluster evaluation of 80% accuracy. After that classifier model was trained using various machine language (ML) algorithms and subsequently tested on mutually exclusive data sets with an objective to predict equipment breakdown. The classifier model using ML algorithms such as Support Vector Machine (SVM) and Decision Tree (DT) returned an accuracy and true positive rate (TPR) of greater than 95% to predict equipment failure. The proposed model acts as an Advanced Intelligent Control system contributing to the Cyber-Physical Systems for asset intensive organizations.

show abstract

How harsh work environments affect the occupational accident phenomenology? Risk assessment and decision making optimisation

Cited by 20 publications

References 10 publications

ATEX-HOF Methodology: Innovation Driven by Human and Organizational Factors (HOF) in Explosive Atmosphere Risk Assessment

ATEX-HOF Methodology: Innovation Driven by Human and Organizational Factors (HOF) in Explosive Atmosphere Risk Assessment

Creating a Comprehensive Method for the Evaluation of a Company

Using Machine Learning Algorithms on data residing in SAP ERP Application to predict equipment failures

Contact Info

Product

Resources

About