面向铁路维护的提升式在线学习与迁移

advanced sensor technologies 与 deep learning algorithms 的集成已 revolutionizes fault diagnosis in railway systems， particularly at the wheel-track interface。尽管已提出 numerous models to detect irregularities such as wheel out-of-roundness，但它们 often fall short in real-world applications due to the dynamic and nonstationary nature of railway operations。本文引入 BOLT-RM（Boosting-inspired Online Learning with Transfer for Railway Maintenance）， a model designed to address these challenges using continual learning for predictive maintenance。通过 allow the model to continuously learn and adapt as new data become available， BOLT-RM overcomes the issue of catastrophic forgetting that often plagues traditional models。It retains past knowledge while improving predictive accuracy with each new learning episode， using a boosting-like knowledge sharing mechanism to adapt to evolving operational conditions such as changes in speed, load, and track irregularities。 methodology is validated through comprehensive multi-domain simulations of train-track dynamic interactions， which capture realistic railway operating conditions。 The proposed BOLT-RM model demonstrates significant improvements in identifying wheel anomalies， establishing a reliable sequence for maintenance interventions。