The role of artificial intelligence and machine learning in mechanical engineering: A review

Abstract

This paper presents a review of the role of artificial intelligence (AI) and machine learning (ML) in advancing mechanical engineering, with an emphasis on domain-specific implementations that have driven recent technological progress. Applications such as predictive maintenance, structural integrity assessment, intelligent design optimization, automated quality inspection, and renewable energy system enhancement demonstrate the capacity of AI approaches, including deep neural networks and reinforcement learning, to improve performance efficiency, minimize operational costs, and foster sustainable engineering solutions. Beyond individual applications, the review discusses fundamental AI attributes, including model adaptability, interpretability, and the coupling of data-driven techniques with physics-informed frameworks, which collectively enable scalable adoption across mechanical engineering disciplines. Notwithstanding these advances, unresolved issues persist, particularly in terms of model reliability, computational overhead, and the availability of high-quality data. By consolidating recent research outcomes, highlighting existing limitations, and proposing prospective research pathways, this review aims to provide valuable insights for both academic researchers and industry.