Identifying shutdown initiating event (SDIE) is critical for developing low power shutdown probabilistic risk assessment for nuclear power plants. Existing computational approaches cannot achieve satisfactory performance because of the challenges of unavailable large, labeled datasets, imbalanced event types, and label noise. To address the challenges, we propose a hybrid pipeline that integrates a knowledge-informed machine learning mode to prescreen Non-SDIEs and a large language model (LLM) to classify SDIEs into four types. In the prescreening stage, we proposed a set of 44 SDIE text patterns that consist of the most salient keywords and phrases from six SDIE types. Text vectorization based on the SDIE patterns generates feature vectors that are highly separable by using a simple binary classifier. The second stage builds BERT-based LLM, which learns generic English language representations from self-supervised pretraining on a large dataset and adapts to SDIE classification by fine-tuning on an SDIE dataset. The proposed approaches are evaluated on a dataset with 10,928 events using precision, recall ratio, F_1 score, and average accuracy. The results demonstrate that the prescreening stage can exclude more than 97% Non-SDIEs, and the LLM achieves an average accuracy of 93.4% for SDIE classification.
