Environmentally Robust Triboelectric Tire Monitoring System for Self‐Powered Driving Information Recognition via Hybrid Deep Learning in Time‐Frequency Representation

Abstract

Developing a robust artificial intelligence of things (AIoT) system with a self‐powered triboelectric sensor for harsh environment is challenging because environmental fluctuations are reflected in triboelectric signals. This study presents an environmentally robust triboelectric tire monitoring system with deep learning to capture driving information in the triboelectric signals generated from tire‐road friction. The optimization of the process and structure of a laser‐induced graphene (LIG) electrode layer in the triboelectric tire is conducted, enabling the tire to detect universal driving information for vehicles/robotic mobility, including rotation speeds of 200–2000 rpm and contact fractions of line. Employing a hybrid model combining short‐term Fourier transform with a convolution neural network‐long short‐term memory, the LIG‐based triboelectric tire monitoring (LTTM) system decouples the driving information, such as traffic lines and road states, from varied environmental conditions of humidity (10%–90%) and temperatures (50–70 °C). The real‐time line and road state recognition of the LTTM system is confirmed on a mobile platform across diverse environmental conditions, including fog, dampness, intense sunlight, and heat shimmer. This work provides an environmentally robust monitoring AIoT system by introducing a self‐powered triboelectric sensor and hybrid deep learning for smart mobility.

Inverse design of Bézier curve-based mechanical metamaterials with programmable negative thermal expansion and negative Poisson's ratio via a data augmented deep autoencoder

“…21,22 Deep learning is a field of machine learning that utilizes an artificial neural network that mimics a human neural network to perform various high-level tasks such as image recognition, natural language processing, active control, signal processing, and manufacturing process optimization that are difficult to solve with conventional methods. [28][29][30][31][32][33] Recently, the deep learning-based inverse design method has risen as an alternative to address the challenges of structure inverse design. Several studies have been conducted to utilize deep learning for the efficient inverse design of various structures with complex and nonlinear mechanisms, such as thermal metamaterials, acoustic metamaterials, electromagnetic metamaterials, composites, and airfoils.…”