Evaluating risk propagation in renewable energy incidents using ontology-based Bayesian networks extracted from news reports

Accidents in the booming renewable energy industries can negatively impact people, animals, and buildings in social systems and ecosystems. Many studies focus on the renewable energy incidents in a single wind-based, solar-based, or hydro-based system, and lack holistic views of incident risk management covering all the systems. This paper proposes a framework for evaluating the comprehensive and cross-system renewable energy incidents by ontology-based Bayesian networks extracted from incident reports using text mining methods. An ontology for renewable energy incidents involving 34 classes, 241 instances, and 352 properties is first created based on knowledge and a hand-annotated dataset with 2 237 event statements. Then the ontology is used to filter and map risk factors and their relations extracted from 11 504 renewable energy incident news reports into nodes and edges in a multi-graph. Finally, the multi-graph is utilized to learn Bayesian networks for modeling renewable energy incident risk propagation, which is evaluated and analyzed by Bayesian inference algorithms. The result shows that there are significant and widespread risk propagation effects in different renewable energy systems, especially the “Separation-Falling-Injury-Fatality” risk transmission chain in the wind-based systems. Fire, collision, deformation, wearing, and falling risks contribute the most to the consequences like damages, fatalities, and failure, and the combined effect of risk elements in the risk transmission chains is the deep-seated reason for generating those consequences for renewable energy incidents. The proposed framework provides new insights into risk analysis for the security planning and construction of renewable energy systems.