Applications of digital technologies and artificial intelligence in automotive material durability assessment: Potential and future trends

Abstract

Amid the automotive industry’s rapid shift toward electrification, autonomous driving, and sustainability, inspection and durability assessment of automotive materials are becoming increasingly critical to ensure safety, optimize performance, and reduce production costs. Traditional experimental methods—mechanical testing (tension, compression, fatigue, impact) and non-destructive testing (ultrasonic, X-ray, magnetic)—are widely used but still have limitations, including high cost, lengthy execution time, and difficulty in accurately predicting material behavior under real operating conditions. The remarkable advances in digital technologies and artificial intelligence (AI) have opened new avenues for this field. Numerical simulation tools such as computer-aided engineering (CAE), the finite element method (FEM), and digital twins enable more accurate prediction of material responses under diverse loading scenarios. In parallel, machine learning (ML) and deep learning (DL) have proved effective in processing large datasets, recognizing material microstructures, and detecting damage from images or sensor signals. This paper provides an overview of recent research on the application of digital technologies and AI to durability evaluation of automotive materials, while comparing analogous applications in the construction sector to extract cross-disciplinary lessons. On this basis, the paper discusses key advantages, remaining challenges, and proposes future directions, aiming toward intelligent, automated, and sustainable material inspection systems.