Understanding complex blasting operations: A structural equation model combining Bayesian networks and latent class clustering. (August 2019)

• Record Type: Journal Article
• Authors: Gerassis, S.; Albuquerque, M.T.D.; García, J.F.; Boente, C.; Giráldez, E.; Taboada, J.; Martín, J.E.
• Is Part Of: Reliability engineering & system safety. Volume 188(2019)
• Page Start: 195
• Page End: 204
• Publication Date: 2019-08
• Subjects: Decision making -- Bayesian learning -- Complex systems -- Risk analysis -- Structural design -- Blasting accidents; Reliability (Engineering) -- Periodicals; System safety -- Periodicals; Industrial safety -- Periodicals; Fiabilité -- Périodiques; Sécurité des systèmes -- Périodiques; Sécurité du travail -- Périodiques; 620.00452
• DOI: 10.1016/j.ress.2019.03.032
• Languages: English
• ISSNs: 0951-8320

Abstract

Highlights: Workplace scenarios using explosives are analyzed with a Bayesian approach based on artificial intelligence (AI). Workers at different corporate hierarchies can engage with Bayesian modeling. Blasting design and corporate accountability are the main drivers of accidents. Uncertainty reduction is computed for accident risk groups. Latent class analysis can avoid cognitive biases in safety policy formulation. Abstract: A probabilistic Structural Equation Model (SEM) based on a Bayesian network construction is introduced to perform effective safety assessments for technicians and managers working on-site. Using novel AI software, the introduced methodology aims to show how to deal with complex scenarios in blasting operations, where typologically different variables are involved. Sequential Bayesian networks, learned from the data, were developed while variables were grouped into different clusters, representing related risks. From each cluster, a latent variable is induced giving rise to a final Bayesian network where cause and effect relationships maximize the prediction of the accident type. This hierarchical structure allows to evaluate different operational strategies, as well as analyze using information theory the weight of the different risk groups. The results obtained unveil hidden patterns in the occurrence of accidents due to flyrock phenomena regarding the explosive employed or the work characteristics. The integration of latent class clustering in the process proves to be an effective safeguard to categorize the variable of interest outside of personal cognitive biases. Finally, the model design and the software applied to show a flexible workflow, where workers at different corporate levels can feel engaged to try their beliefs to design safety interventions.