Incremental learning model for dynamical identification and classification of abnormal vibration in operational underground facilities.

• An incremental model to identify abnormal vibrations is proposed. • Rehearsal and knowledge distillation prevent catastrophic forgetting. • Metric function is used to distinguish the feature distribution of each category. • VAE is also used for identifying new types of abnormal vibrations. Underground infrastructures are rapidly growing in size and complexity. However, their operations are affected by several hazards, including hidden structural deterioration and effects of random external constructions. Dynamic monitoring of these hazards is essential to provide early warning. We propose a vibration-based self-supervised incremental learning model for dynamic monitoring of emerging operational threats by recognizing abnormal responses. The model comprises teacher and student models based on a variational autoencoder (VAE) with a metric function. When the teacher model detects a new category of abnormal vibration, the student model is trained to recognize this abnormality through sample rehearsals and knowledge distillations. Subsequently, it becomes the teacher model for the next round of incremental learning. We demonstrate through a case study that catastrophic forgetting can be avoided and memory consumption can be reduced during dynamic network updates. Moreover, the use of a metric function in the VAE increases the vibration identification accuracy. [ABSTRACT FROM AUTHOR]