Massive and complex unstructured fault text data will be generated during the operation of subway trains. A named entity recognition model of subway on-board equipment based on Multiheaded Self-attention mechanism and CNN-BiLSTM-CRF is proposed to address the issue of low recognition accuracy and incomplete recognition features of unstructured fault data named entity recognition task of subway on-board equipment: BiLSTM-CNN parallel network extracts context feature information and local attention information, respectively; In the MHA layer, the features learned from different dimensions are fused through the Multiheaded Self-attention mechanism, and the dependencies of various ranges in the sequence are captured to yield the internal structure information of the features. The conditional random field CRF is used to learn the internal relationship between tags to ensure their sequence. This model is tested with other named entity recognition models on the marked subway on-board fault data. The experimental results demonstrate that this model is able to recognize 10 kinds of labels in the dataset. Moreover, the recognition effect of each label has a good performance in the three evaluation indexes of P, R, and F1 score. Moreover, the weighted average evaluation indexes
Avg
−
P
,
Avg
−
R
, and
Avg
−
F
1
of 10 labels in this model reach the highest 95.39%, 95.48%, and 95.37%, which has high evaluation indexes and can be applied to the named entity recognition of Metro on-board equipment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.