Zhang Zeyi

Mr. Zhang Zeyi

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 October 2025 in Ocean Engineering
Verified
Journal Article
Closed access
SLShuangtao Liu
Shuangtao Liu
YLYuhong Liu
Yuhong Liu
ZZZhang Zeyi
Zhang Zeyi
HBHuan Bai
Huan Bai
JDJinyang Du
Jinyang Du
BCBoning Cao
Boning Cao

26 April 2024 in International Journal of Control, Automation, and Systems
Verified
Journal Article
Closed access
PDF file
XLXiaokang Li
Xiaokang Li
SWShuxin WANG
Shuxin WANG
YLYuhong Liu
Yuhong Liu
HBHuan Bai
Huan Bai
ZZZhang Zeyi
Zhang Zeyi

15 May 2024 in Proceedings
Verified
Conference Paper
Open access
PDF file
ZZZhang Zeyi
Zhang Zeyi
YLYuhong Liu
Yuhong Liu
HLHoucun Li
Houcun Li
JDJinyang Du
Jinyang Du
WWWenchao Wang
Wenchao Wang
HBHuan Bai
Huan Bai
Otariidae are the only marine mammals that use their foreflippers for propulsion, and the combination of hydrofoil and paddle propulsion makes them excellent hunters and swimmers. Therefore, it is of great scientific significance and engineering value to develop a novel underwater propulsion technology inspired by the propulsion mode of Otariidae foreflippers. At present, research on the Otariidae foreflipper-inspired propulsion is still in the initial stage and needs to be explored further in terms of both theory and technology. The bionic underwater robot team led by Prof. Liu of Tianjin University has made some achievements in this regard. Taking the California sea lion as a bionic prototype, they developed the first-generation biomimetic robotic sea lion foreflipper propulsion mechanism (Rob-flipper-I for short). In this study, the Rob-flipper-II is developed through the optimization of the Rob-flipper-I, which is composed of a driving mechanism and a pair of bionic foreflippers. The driving mechanism consists of a wobbling disk mechanism and a spatial linkage mechanism that are connected in series, and the bionic foreflippers have similar flexibility and mechanical properties to those of the sea lion foreflippers. The Rob-flipper-II can reproduce the spatial trajectory and attitude of the sea lion foreflippers by a single drive only. Based on the kinematics analysis of the Rob-flipper-II, the formulas for calculating the thrust and lift of the bionic foreflipper are derived, and the functional relationship between the motion speed of the bionic sea lion robot and the flapping frequency of the bionic foreflippers are obtained. In addition, the propulsive efficiency of the Rob-flipper-II is calculated. The tank experiment shows that the average thrust and propulsive efficiency of the Rob-flipper-II are higher than those of the Rob-flipper-I.

Verified
Journal Article
Open access
PDF file
ZZZhang Zeyi
Zhang Zeyi
YLYuhong Liu
Yuhong Liu
SLShuangtao Liu
Shuangtao Liu
SLShiquan Lan
Shiquan Lan
WNWendong Niu
Wendong Niu
HBHuan Bai
Huan Bai
Yaw regulation of biomimetic underwater robots is complicated by flexible body motion, nonlinear hydrodynamics, and coupled actuation. This study examines whether a policy trained in simulation can be deployed on an existing robotic sea lion (RSL) without changing its hardware or low-level controllers. A deep deterministic policy gradient (DDPG) controller was formulated from measurable states and available actuator commands and trained in Webots using a model calibrated from previous tank tests. Four manually selected reward-weight settings and command update rates of 1, 2, 5, and 10 Hz were examined as deployment-oriented sensitivity comparisons, after which a 5 Hz policy was evaluated in six tank trials. Performance was reanalyzed using the circular-angle mean absolute error (MAE) and root mean square error (RMSE). In the two straight-swimming trials, the per-trial MAE was 1.01–1.12°, and the RMSE was 1.10–1.46°. In the four turning trials, evaluated from the first target crossing to the end of each record, the MAE was 1.71–3.63°, the RMSE was 2.10–4.20°, and the maximum overshoot was 2.99–7.70°. Despite the transient differences between simulations and experiments, the controller regulated the robot toward the target headings in all six tank trials. These results demonstrate the successful sim-to-real deployment of reinforcement-learning-based yaw control under low-frequency communication constraints and provide experimental evidence for its application to biomimetic underwater robots.