With the rapid development of intelligent technologies in aviation, electric vertical take-off and landing (eVTOL) aircraft have emerged as key players in the low-altitude economy, their battery performance directly impacts safety and cost, making accurate prediction essential. This paper presents a comprehensive review of the literature on battery degradation prediction methods for eVTOL aircraft, providing a brief overview on early modeling approaches and placing primary emphasis on recent advances in their applicability and limitations under unique operational scenarios of eVTOL, such as frequent takeoffs and landings, high power loads, and complex environmental conditions. Current prediction efforts primarily target key indicators including battery lifespan, health status, and capacity retention, employing a range of technical approaches such as electrochemical modeling, equivalent circuit modeling, data-driven algorithms like machine learning and deep learning, and hybrid physics-informed models that integrate domain knowledge with data analysis. The review systematically summarizes the main prediction methods and their evolution in different phases of the development of eVTOL technology. On this basis, we highlight existing technical bottlenecks and unresolved challenges, including the high demand for data and computational resources limiting real-time performance, poor accuracy of traditional models under high discharge rates and extreme conditions, challenges in accurately modeling complex multi-physics interactions and achieving a stable balance among prediction accuracy, interpretability, and real-time computational efficiency, as well as the scarcity of historical flight data affecting model reliability and generalization. This review also proposes future research directions to enhance the reliability and accuracy of battery degradation forecasting for eVTOL applications.
扫码关注我们
求助内容:
应助结果提醒方式:
