@article{Yu2026, 
author = {Yue Yu and Zeyun Yang and Xiaohui Zhang and Xinkang Li and Jianhui Yi and Deshui Han},
title = {Brain-inspired memory architecture for condition monitoring based on hippocampal-neocortical complementary learning},
year = {2026},
journal = {High-speed Railway},
volume = {4},
number = {2},
pages = {89-98},
keywords = {Continual learning, Complementary learning systems, Principal component analysis, Condition monitoring},
url = {https://www.sciopen.com/article/10.1016/j.hspr.2025.11.001},
doi = {10.1016/j.hspr.2025.11.001},
abstract = {This paper tackles the critical challenge of catastrophic forgetting and inefficient learning in artificial intelligence models processing continuous, non-stationary data streams. Inspired by neurobiological mechanisms, specifically the Complementary Learning Systems (CLSs) theory involving the hippocampus and neocortex, we propose a novel brain-inspired biomimetic memory system. The core innovation integrates dimensionality reduction techniques—covariance decomposition and low-dimensional mapping—for efficient feature extraction from long spatiotemporal-scale information flows, with a biomimetic learning/forgetting mechanism grounded in CLS principles. Evaluated on real-world power plant operational data, the proposed system demonstrates robust performance against noise and fluctuations, validating the effectiveness of the bionic learning/forgetting mechanism.}
}