Research Review on Atkinson Cycle Internal Combustion Engines: Technological Development and Optimization Strategies

Abstract

This paper provides a comprehensive review of the principles, characteristics, and application prospects of Atkinson Cycle internal combustion engines in hybrid vehicles. It delves into the crucial role of fluid mechanics in optimizing cylinder design for Atkinson cycle engines, emphasizing its importance in improving engine efficiency, fuel economy, and overall performance. The paper contrasts traditional fluid mechanics research methods, such as computational fluid dynamics (CFD) and empirical testing, with machine learning approaches, showcasing the latter’s transformative impact on research precision and efficiency. Through an in-depth analysis of machine learning techniques—such as clustering, modal decomposition, neural networks, and ensemble learning—it elaborates on their application methods, strengths, and potential to accelerate research processes in the study of Atkinson cycle engines. The review highlights how machine learning can enhance simulation accuracy, reduce computational costs, and predict complex flow behaviors, making it a valuable tool for advanced engine research. Additionally, it discusses the integration of these approaches into hybrid vehicle design, providing valuable insights for engineers and researchers. This paper serves as a reference for innovation and technological development, offering guidance for future advancements in internal combustion engine research and hybrid powertrain optimization.