Study on Intelligent Extraction of Requirements for MBSE Modeling of Train Control System

The development of urban rail transit has diversified communication infrastructure needs, and the design of Communication-Based Train Control(CBTC) system is critical to improving passenger service quality. To ensure that all requirements are accurately communicated and traceable during the model design process, this paper conducts CBTC system modeling work based on model system engineering concepts. Requirements extraction, as a key step in system design and development, directly affects system performance, but traditional requirements extraction methods rely on manual analysis, which is time-consuming and error-prone. In this regard, this paper proposes a requirement extraction framework based on Named Entity Recognition (NER) technology, including requirement document preprocessing, key requirement extraction by BERT-BiLSTM-CRF and automated generation of requirement entries, and two sets of comparative experiments were conducted, and the results show that the model realizes the best performance in the CBTC Requirements extraction task, with an accuracy of 99.13%, and reduces the manual intervention in the demand extraction process.