Liang Li

Dr. Liang Li

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
1 June 2021 in Ocean Engineering
Verified
Journal Article
Closed access
LLLiang Li
Liang Li
BZBin Zhou
Bin Zhou
HHHongbo Huang
Hongbo Huang
HSHongxing Sun
Hongxing Sun

11 April 2023 in Ocean Engineering
Verified
Journal Article
Closed access
LLLiang Li
Liang Li
YCYihong Chen
Yihong Chen
YQYiming Qiang
Yiming Qiang
BZBin Zhou
Bin Zhou
WCWeizheng Chen
Weizheng Chen

14 November 2024 in Applied Ocean Research
Verified
Journal Article
Closed access
LLLiang Li
Liang Li
YCYihong Chen
Yihong Chen
SXShuo Xie
Shuo Xie
YXYucheng Xiao
Yucheng Xiao
TFTian Fang
Tian Fang
CWChao Wang
Chao Wang

Verified
Journal Article
Open access
PDF file
LLLiang Li
Liang Li
YCYihong Chen
Yihong Chen
LHLu Huang
Lu Huang
QHQing Hai
Qing Hai
DTDenghai Tang
Denghai Tang
CWChao Wang
Chao Wang
A multitask learning (MTL) model based on artificial neural networks (ANNs) is proposed in this study to improve the prediction accuracy and physical reliability of marine propeller hydrodynamic performance. The propeller’s comprehensive geometric features are used as inputs, and the coefficients of quadratic polynomials for the thrust coefficient (KT) and torque coefficient (10KQ) curves are predicted as outputs. The loss function is customized through a positive gradient penalty of the curves to accelerate training. When the single-task and multitask models were compared, the prediction errors were reduced; KT decreased from 2.61% to 2.07%, 10 KQ decreased from 3.58% to 2.31%, and the efficiency (η) decreased from 3.04% to 2.00%. Non-physical fluctuations in the performance curves were effectively mitigated by the multitask model, yielding predicted curvatures which closely matched the experimental data. Strong generalization was demonstrated when the model was tested on unseen propellers, with deviations of 2.2% for KT, 4.6% for 10 KQ, and 3.8% for η. Finally, the model was applied to optimize the propeller design for a 325,000 ton very large ore carrier ship, where a Pareto front with 58 non-dominant solutions for the maximum speed and fluctuating pressure was successfully generated and effectively verified by the model’s test results. The model enhanced the prediction of the propeller performance and contributed to optimization in the propeller’s design.

Verified
Journal Article
Open access
PDF file
LLLiang Li
Liang Li
BZBin Zhou
Bin Zhou
DLDengcheng Liu
Dengcheng Liu
CWChao Wang
Chao Wang
The numerical calculation was performed for the KRISO Container Ship (KCS) hull-propeller-rudder system with different freedom hull motion by employing the Reynolds-Averaged Navier-Stokes (RANS) method and adopting the overset grid. Firstly, the numerical simulation of hydrodynamics for a bare hull with the heave and pitch motion is carried out. The results show that the space non-uniformity of a nominal wake in the disk plane with motion is comparable to the case without motion. However, the time non-uniformity increases sharply and it has a significant positive relationship with the motion amplitude. Then, the propeller exciting force is calculated in the case including single heave, single pitch and their couple motion. It was found that both the ship and propeller hydrodynamic performance deteriorated dramatically due to the hull motion. Furthermore, the spectrum peak at the motion frequency is dominant in all the peak values and the larger the amplitude is, the higher the motion frequency peak is expected to be. For the propeller bearing force, the effect of the different hull motions appears as linear superimposition. However, the superimposition of different hull motions enlarges the propeller-induced fluctuating pressure in a single motion.

8 May 2024 in Ocean Engineering
Verified
Journal Article
Closed access
YCYihong Chen
Yihong Chen
LLLiang Li
Liang Li
HXHui Xia
Hui Xia
LHLu Huang
Lu Huang
JLJiang Lv
Jiang Lv