Advances in machine learning-based active vibration control for automotive seat suspensions: A comprehensive review
Yuli Zhao, Yihe Zhang, Linchuan Guo, Songlin Ding, Xu Wang
Abstract
With the rise of intelligent vehicles , the driving and riding experience has undergone significant changes. However, research on intelligent active vibration control of seat suspension systems, which is closely related to ride comfort and safety, remains in its early stages. This paper explores novel machine learning-based control algorithms and their potential applications in active vibration control of seat suspension systems, particularly how the algorithms such as supervised learning, unsupervised learning , and reinforcement learning (RL) can overcome the limitations of traditional control methods. Given the lack of comprehensive reviews in this field, this paper aims to provide researchers with a systematic analysis by reviewing machine learning algorithms and their successful applications in other domains and discussing their application potential in active vibration control of seat suspension systems. In doing so, it seeks to offer new insights for the intelligent development of this field.