Creating an incident investigation framework for a complex socio-technical system: Application of multi-label text classification and Bayesian network structure learning

•An innovative approach to identify the accident causal factors and their complex relationships in socio-technical systems is developed.•The developed framework is applicable for targeted risk management and accident prevention in complex socio-technical systems.•To prevent the manual analysis of a...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Reliability engineering & system safety Ročník 260; s. 110971
Hlavní autoři: Karimi Dehkordi, Mohammadreza, Sattari, Fereshteh, Lefsrud, Lianne
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.08.2025
Témata:
Bayesian network structure learning
Causal analysis
Human and organizational factors
Incident investigation
Multi-label text classification
Power distribution
Socio-technical system
Multi-label text classification
Human and organizational factors
Causal analysis
Socio-technical system
Bayesian network structure learning
Incident investigation
Power distribution
ISSN:0951-8320
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•An innovative approach to identify the accident causal factors and their complex relationships in socio-technical systems is developed.•The developed framework is applicable for targeted risk management and accident prevention in complex socio-technical systems.•To prevent the manual analysis of a large number of incident reports, replete with textual content, multi-label text classification is used to classify the reports.•Bayesian network structure learning is employed to identify causal and co-occurrence relationships among technical, human, environmental, and organizational factors, as well as their relative importance in the occurrence of accidents. The power distribution sector presents a complex socio-technical system where accidents frequently occur from various technical, human, environmental, and organizational factors, resulting in fatalities and substantial economic losses. The dynamic operational environment and complex interactions among the causal factors further complicate effective risk management and accident prevention. This research proposes a methodology to identify various risk factors and develop causal networks representing the complex relationships among these factors in power distribution incident reports. First, machine learning multi-label text classification identifies the risk factors from the incident reports. Then, the relationship among these factors is determined by integrating experts’ domain knowledge and data-driven Bayesian network structure learning approaches. Finally, the most influential causal factors and their direct/indirect effects on the incidents are identified, and proper risk control measures are recommended. The proposed methodology is applied to an incident database from a Canadian power distribution company, covering power outages, injuries, environmental issues, and near misses collected from 2013 to 2020. The results highlight that human and technical factors are the most influential and affected by organizational and environmental factors. Considering their complex interaction, implementing targeted risk management for high-risk direct/indirect causal factors could prevent further incidents and improve the companies’ overall safety.
ISSN:0951-8320
DOI:10.1016/j.ress.2025.110971