A multi-node self-powered fault detection system by triboelectric-electromagnetic nanosensors for smart transportation

Abstract

The harnessing of vibrational energy is becoming increasingly pivotal in the development of intelligent rail transit systems. The integration of emerging technologies such as triboelectric nanogenerators (TENGs), electromagnetic generators (EMGs), or hybrid generators has become crucial for fault detection and energy harvesting in rail transit. This paper introduces a self-powered fault detection system (SPFDS). SPFDS combines multiple compact rotating Triboelectric-Electromagnetic Nanosensor (TENS) nodes with a deep learning-based diagnostic module to transform vibrational energy generated during train operations into electrical power and accurately identifies five distinct train bogie fault conditions. Simulations and experiments have shown that the TENS nodes, with a root mean square power of 0.21 W and a power density of 1595.7 W/m³, can efficiently detect various bogie faults. Additionally, their power output is adequate to support commercial sensors and Bluetooth modules. Through hyperparameter optimization, the diagnostic module utilizing multi-TENS nodes achieves an average diagnostic accuracy of 99.38 % for the five fault modes of freight train bogies. Implementing multiple TENS nodes in SPFDS enhances fault detection accuracy by an average of 32 % compared to a single TENS node, with a peak increase of 128 %. The multi-node TENS configuration and SPFDS's self-powered detection capabilities represent an innovative approach to complex fault detection, significantly contributing to the advancement of vibration energy harvesting and the development of distributed self-powered sensor network technologies for smart transportation.