Xiaodi Liu

Xiaodi Liu

Auto-generated profile, based on publicly available information

Xiaodi Liu

College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen, China

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
1 November 2019 in Science Advances
Verified
Journal Article
Open access
PDF file
Jiang MaJiang Ma
Jiang Ma
CYCan Yang
Can Yang
XLXiaodi Liu
Xiaodi Liu
BSBaoshuang Shang
Baoshuang Shang
QHQuanfeng He
Quanfeng He
Yong YangYong Yang
Yong Yang
We developed a facile ultrasonic vibration route is developed to synthesize BMGs and metallic glass-glass composites.

23 January 2023 in npj Computational Materials
Verified
Journal Article
Open access
PDF file
ZZZiqing Zhou
Ziqing Zhou
YSYinghui Shang
Yinghui Shang
XLXiaodi Liu
Xiaodi Liu
Yong YangYong Yang
Yong Yang
The design of bulk metallic glasses (BMGs) via machine learning (ML) has been a topic of active research recently. However, the prior ML models were mostly built upon supervised learning algorithms with human inputs to navigate the high dimensional compositional space, which becomes inefficient with the increasing compositional complexity in BMGs. Here, we develop a generative deep-learning framework to directly generate compositionally complex BMGs, such as high entropy BMGs. Our framework is built on the unsupervised Generative Adversarial Network (GAN) algorithm for data generation and the supervised Boosted Trees algorithm for data evaluation. We studied systematically the confounding effect of various data descriptors and the literature data on the effectiveness of our framework both numerically and experimentally. Most importantly, we demonstrate that our generative deep learning framework is capable of producing composition-property mappings, therefore paving the way for the inverse design of BMGs.

23 August 2021 in npj Computational Materials
Verified
Journal Article
Open access
PDF file
ZZZ. Q. Zhou
Z. Q. Zhou
QHQ. F. He
Q. F. He
XLX. D. Liu
X. D. Liu
QWQ. Wang
Q. Wang
JLJ. H. Luan
J. H. Luan
Yong YangYong Yang
Yong Yang
The compositional design of metallic glasses (MGs) is a long-standing issue in materials science and engineering. However, traditional experimental approaches based on empirical rules are time consuming with a low efficiency. In this work, we successfully developed a hybrid machine learning (ML) model to address this fundamental issue based on a database containing ~5000 different compositions of metallic glasses (either bulk or ribbon) reported since 1960s. Unlike the prior works relying on empirical parameters for featurization of data, we designed modeling guided data descriptors in line with the recent theoretical models on amorphization in chemically complex alloys for the development of the hybrid classification-regression ML algorithms. Our hybrid ML modeling was validated both numerically and experimentally. Most importantly, it enabled the discovery of MGs (either bulk or ribbon) through the ML-aided deep search of a multitude of quaternary to scenery alloy compositions. The computational framework herein established is expected to accelerate the design of MG compositions and expand their applications by probing the complex and multi-dimensional compositional space that has never been explored before.

3 September 2024 in npj Computational Materials
Verified
Journal Article
Open access
PDF file
ZCZ. Q. Chen
Z. Q. Chen
YSY. H. Shang
Y. H. Shang
XLX. D. Liu
X. D. Liu
Yong YangYong Yang
Yong Yang
Eutectic alloys have garnered significant attention due to their promising mechanical and physical properties, as well as their technological relevance. However, the discovery of eutectic compositionally complex alloys (ECCAs) (e.g. high entropy eutectic alloys) remains a formidable challenge in the vast and intricate compositional space, primarily due to the absence of readily available phase diagrams. To address this issue, we have developed an explainable machine learning (ML) framework that integrates conditional variational autoencoder (CVAE) and artificial neutral network (ANN) models, enabling direct generation of ECCAs. To overcome the prevalent problem of data imbalance encountered in data-driven ECCA design, we have incorporated thermodynamics-derived data descriptors and employed K-means clustering methods for effective data pre-processing. Leveraging our ML framework, we have successfully discovered dual- or even tri-phased ECCAs, spanning from quaternary to senary alloy systems, which have not been previously reported in the literature. These findings hold great promise and indicate that our ML framework can play a pivotal role in accelerating the discovery of technologically significant ECCAs.

5 December 2023 in Nature Materials
Verified
Journal Article
Closed access
PDF file
FLFucheng Li
Fucheng Li
ZZZhibo Zhang
Zhibo Zhang
HLHuanrong Liu
Huanrong Liu
WZWenqing Zhu
Wenqing Zhu
TWTianyu Wang
Tianyu Wang
Yong YangYong Yang
Yong Yang

12 February 2021 in RSC Advances
Verified
Journal Article
Open access
PDF file
KAK. S. Aneeshkumar
K. S. Aneeshkumar
JTJo-Chi Tseng
Jo-Chi Tseng
XLXiaodi Liu
Xiaodi Liu
JTJinsen Tian
Jinsen Tian
DDDongfeng Diao
Dongfeng Diao
Jun ShenJun Shen
Jun Shen
The anion exchange membrane (AEM) in fuel cells requires new, stable, and improved electrocatalysts for large scale commercial production of hydrogen fuel for efficient energy conversion. Fe40Ni20Co20P15C5, a novel metallic glass ribbon, was prepared by arc melting and melt spinning method. The metallic glass was evaluated as an efficient electrocatalyst in water-splitting reactions, namely hydrogen evolution reaction under acidic and alkaline conditions. In addition, oxygen evolution reaction in alkaline medium was also evaluated. In 0.5 M H2SO4, the metallic glass ribbons, after electrochemical dealloying, needed an overpotential of 128 mV for hydrogen evolution reaction, while in 1 M KOH they needed an overpotential of 236 mV for hydrogen evolution. For the oxygen evolution reaction, the overpotential was 278 mV. The electrochemical dealloying procedure significantly reduced the overpotential, and the overpotential remained constant over 20 hours of test conditions under acidic and alkaline conditions. The improved electrocatalytic activity was explained based on the metastable nature of metallic glass and the synergistic effect of metal hydroxo species and phosphates. Based on the excellent properties and free-standing nature of these metallic glass ribbons in electrolyte medium, we propose the current metallic glass for commercial, industrial electrocatalytic applications.