Search

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. [ABSTRACT FROM AUTHOR]

The surge of renewable energy systems can lead to increasing incidents that negatively impact economics and society, rendering incident detection paramount to understand the mechanism and range of those impacts. In this paper, a deep learning framework is proposed to detect renewable energy incidents from news articles containing accidents in various renewable energy systems. The pre-trained language models like Bidirectional Encoder Representations from Transformers (BERT) and word2vec are utilized to represent textual inputs, which are trained by the Text Convolutional Neural Networks (TCNNs) and Text Recurrent Neural Networks. Two types of classifiers for incident detection are trained and tested in this paper, one is a binary classifier for detecting the existence of an incident, the other is a multi-label classifier for identifying different incident attributes such as causal-effects and consequences, etc. The proposed incident detection framework is implemented on a hand-annotated dataset with 5 190 records. The results show that the proposed framework performs well on both the incident existence detection task (F1-score 91.4%) and the incident attributes identification task (micro F1-score 81.7%). It is also shown that the BERT-based TCNNs are effective and robust in detecting renewable energy incidents from large-scale textual materials. [ABSTRACT FROM AUTHOR]