Zhixu Duan

Zhixu Duan

he/him

To the next, to the top

About Me

To the next, to the top.

I am Zhixu Duan (ๆฎตไน‹็ปญ), an undergraduate at SMEE (School of Mechanical and Electrical Engineering) of UESTC (University of Electronic Science and Technology, China), major in mechanical engineering. Now as RA in Center for System Reliability and Safety, China (ReliaLab), advised by Zuoyi Chen and Hong-Zhong Huang. Also RA in EPICLab (Efficient and Precision Intelligent Computing Lab), SAI of SJTU (School of Artificial Intelligence, Shanghai Jiao Tong University),advised by Linfeng Zhang.

relialab
sai

Ask me anything! Always keep a passion for exploring strange fields . Research interests focus on AI4Reliability including but are not limited to zero-shot/few-shot learning, transfer learning, and llm.

See my github! zxuuuustupid

GitHub

๐ŸŽ“Education & Background

โ— 2025.11โ€“Present, RA at EPICLab, SAI of SJTU
โ— 2023.12โ€“Present, RA at ReliaLab,UESTC
โ— 2023.9โ€“2027.9, B.S. at SMEE of UESTC.
โ— 2020.9โ€“2023.9, In No.1 Middle School of Huairen, Shanxi Province.

๐Ÿ†Achievements

โ— National Scholarship in 2025 Top 1.8% ย 
โ— National Scholarship in 2024 Top 1.8% ย 
โ— Ranked 1/83 in my major๐Ÿฅ‡ Top 1
โ— Research/Papers๐Ÿ“ƒ

IEEE PHM 2024
PHM

๐Ÿ”ฅ๐๐š๐ซ๐š๐ฅ๐ฅ๐ž๐ฅ ๐‘๐ž๐ฅ๐š๐ญ๐ข๐จ๐ง ๐๐ž๐ญ๐ฐ๐จ๐ซ๐ค ๐Ÿ๐จ๐ซ ๐ˆ๐ง๐ญ๐ž๐ฅ๐ฅ๐ข๐ ๐ž๐ง๐ญ ๐…๐š๐ฎ๐ฅ๐ญ ๐ƒ๐ž๐ญ๐ž๐œ๐ญ๐ข๐จ๐ง ๐š๐ง๐ ๐‹๐จ๐œ๐š๐ฅ๐ข๐ณ๐š๐ญ๐ข๐จ๐ง ๐จ๐Ÿ ๐“๐ซ๐š๐ข๐ง ๐“๐ซ๐š๐ง๐ฌ๐ฆ๐ข๐ฌ๐ฌ๐ข๐จ๐ง ๐’๐ฒ๐ฌ๐ญ๐ž๐ฆ๐ฌ ๐ฐ๐ข๐ญ๐ก ๐™๐ž๐ซ๐จ-๐Ÿ๐š๐ฎ๐ฅ๐ญ ๐’๐š๐ฆ๐ฉ๐ฅ๐ž
โญ๐—™๐—ถ๐—ฟ๐˜€๐˜ ๐—ฎ๐˜‚๐˜๐—ต๐—ผ๐—ฟ and delivered an oral presentation to IEEE PHM 2024
TL;DR: A PRN model combining RSN and KAN is proposed for train transmission fault detection with few samples, achieving over 98% accuracy and strong generalization.

EAAI
EAAI

๐Ÿ”ฅ๐๐ฌ๐ž๐ฎ๐๐จ-๐Ÿ๐š๐ฎ๐ฅ๐ญ ๐๐š๐ญ๐š ๐ž๐ง๐ก๐š๐ง๐œ๐ž๐ ๐ซ๐ž๐ฅ๐š๐ญ๐ข๐จ๐ง ๐ง๐ž๐ญ๐ฐ๐จ๐ซ๐ค ๐Ÿ๐จ๐ซ ๐Ÿ๐š๐ฎ๐ฅ๐ญ ๐๐ž๐ญ๐ž๐œ๐ญ๐ข๐จ๐ง ๐š๐ง๐ ๐ฅ๐จ๐œ๐š๐ฅ๐ข๐ณ๐š๐ญ๐ข๐จ๐ง ๐ข๐ง ๐ญ๐ซ๐š๐ข๐ง ๐ญ๐ซ๐š๐ง๐ฌ๐ฆ๐ข๐ฌ๐ฌ๐ข๐จ๐ง ๐ฌ๐ฒ๐ฌ๐ญ๐ž๐ฆ๐ฌ
โญ๐—™๐—ถ๐—ฟ๐˜€๐˜ ๐—ฎ๐˜‚๐˜๐—ต๐—ผ๐—ฟ published in ๐—˜๐—”๐—”๐—œ (๐—ฆ๐—–๐—œ ๐—ค๐Ÿญ) TL;DR: A relation network using pseudo-fault data improves train transmission fault detection and localization performance.

Under Review
MSSP

๐Ÿ”ฅ๐ƒ๐ž๐œ๐จ๐ฎ๐ฉ๐ฅ๐ข๐ง๐  ๐ˆ๐ง๐ญ๐ซ๐ข๐ง๐ฌ๐ข๐œ ๐…๐š๐ฎ๐ฅ๐ญ ๐…๐ž๐š๐ญ๐ฎ๐ซ๐ž๐ฌ ๐Ÿ๐ซ๐จ๐ฆ ๐ƒ๐จ๐ฆ๐š๐ข๐ง ๐•๐š๐ซ๐ข๐š๐ญ๐ข๐จ๐ง๐ฌ ๐ฏ๐ข๐š ๐ƒ๐จ๐ฆ๐š๐ข๐ง-๐€๐ญ๐ญ๐ซ๐ข๐›๐ฎ๐ญ๐ž ๐…๐ฎ๐ฌ๐ข๐จ๐ง ๐Ÿ๐จ๐ซ ๐”๐ง๐ฌ๐ž๐ž๐ง-๐ƒ๐จ๐ฆ๐š๐ข๐ง ๐…๐š๐ฎ๐ฅ๐ญ ๐ƒ๐ข๐š๐ ๐ง๐จ๐ฌ๐ข๐ฌ
โญ๐—™๐—ถ๐—ฟ๐˜€๐˜ ๐—ฎ๐˜‚๐˜๐—ต๐—ผ๐—ฟ submitted manuscript to ๐— ๐—ฆ๐—ฆ๐—ฃ (๐—ฆ๐—–๐—œ ๐—ค๐Ÿญ) TL;DR: A domain-attribute fusion model decouples intrinsic fault features, improving unseen-domain diagnosis robustness.

Under Review
UHDRL

๐Ÿ”ฅ๐”๐ง๐ข๐Ÿ๐ข๐ž๐ ๐‡๐ž๐š๐ฅ๐ญ๐ก ๐ƒ๐จ๐ฆ๐š๐ข๐ง ๐‘๐ž๐ฅ๐š๐ญ๐ข๐จ๐ง ๐‹๐ž๐š๐ซ๐ง๐ข๐ง๐  ๐Ÿ๐จ๐ซ ๐“๐ซ๐š๐ข๐ง ๐“๐ซ๐š๐ง๐ฌ๐ฆ๐ข๐ฌ๐ฌ๐ข๐จ๐ง ๐’๐ฒ๐ฌ๐ญ๐ž๐ฆ๐ฌ ๐…๐š๐ฎ๐ฅ๐ญ ๐ƒ๐ž๐ญ๐ž๐œ๐ญ๐ข๐จ๐ง ๐ฎ๐ง๐๐ž๐ซ ๐‚๐จ๐ฆ๐ฉ๐ฅ๐ž๐ฑ ๐Ž๐ฉ๐ž๐ซ๐š๐ญ๐ข๐ง๐  ๐‚๐จ๐ง๐๐ข๐ญ๐ข๐จ๐ง๐ฌ
โญ๐—ฆ๐—ฒ๐—ฐ๐—ผ๐—ป๐—ฑ ๐—ฎ๐˜‚๐˜๐—ต๐—ผ๐—ฟ (๐—ณ๐—ถ๐—ฟ๐˜€๐˜ ๐—ฎ๐˜‚๐˜๐—ต๐—ผ๐—ฟ ๐—ผ๐—ณ ๐—ฎ๐—ฑ๐˜ƒ๐—ถ๐˜€๐—ฒ๐—ฟ) submitted manuscript to ๐—œ๐—˜๐—˜๐—˜ ๐—ง๐—œ๐—œ (๐—ฆ๐—–๐—œ ๐—ค๐Ÿญ) TL;DR: A unified health-domain relation learning approach enhances fault detection under complex operating conditions.

Minor Revision
CLIP

๐Ÿ”ฅ๐Ž๐ฉ๐ž๐ง-๐’๐ž๐ญ ๐…๐š๐ฎ๐ฅ๐ญ ๐ƒ๐ข๐š๐ ๐ง๐จ๐ฌ๐ข๐ฌ ๐”๐ฌ๐ข๐ง๐  ๐‚๐‹๐ˆ๐ ๐ฐ๐ข๐ญ๐ก ๐…๐จ๐ซ๐ฐ๐š๐ซ๐-๐‘๐ž๐ฏ๐ž๐ซ๐ฌ๐ž ๐‘๐ž๐š๐ฌ๐จ๐ง๐ข๐ง๐ 
โญ๐—ฆ๐—ฒ๐—ฐ๐—ผ๐—ป๐—ฑ ๐—ฎ๐˜‚๐˜๐—ต๐—ผ๐—ฟ (๐—ณ๐—ถ๐—ฟ๐˜€๐˜ ๐—ฎ๐˜‚๐˜๐—ต๐—ผ๐—ฟ ๐—ผ๐—ณ ๐—ฎ๐—ฑ๐˜ƒ๐—ถ๐˜€๐—ฒ๐—ฟ) submitted manuscript to ๐—–๐—ข๐— ๐—ฃ๐—จ๐—ง ๐—œ๐—ก๐—— (๐—ฆ๐—–๐—œ ๐—ค๐Ÿญ) TL;DR: A CLIP-based forwardโ€“reverse reasoning model enable for fault diagnosis

โ— Second author of an invention patent (first author of adviser), accepted for filing.
โ— Principal leader of a National Innovation and Entrepreneurship Program (College Student Project)

Leadership

โ— Vice President and founding core member of UESTC Interdisciplinary Association (IA).

1.Invited Professor Dezhong Yao (Founding Dean of UESTCโ€™s School of Life Science and Technology) and brain scientist Professor Pedro Antonio Valdes Sosa as advisors
2.To promote the societyโ€™s outreach and research activities in fields such as bioinformatics, bioimaging, bioelectronics, and AI for Life Science.
3.Responsible for building and maintaining the associationโ€™s official website.

ia-flag
ia-overview

โ— Student Mentor for SMEE 2025 Freshmen

Mentored freshmen under the guidance of Counselor Keyu Chen

Talks & Reports

โ— ใ€SMEE idolใ€‘Zhixu Duan:โ€Take Each Step Steadily, and the Distance Will Unfoldโ€ -Interviewed by SMEE of UESTC

Academic Positions

โ— ๐Ÿ˜A key reader of Nature and a potential contributor to Science.
โ— ๐Ÿ˜ŽAttending major international conferences, and leading the field in tea break self-service acquisition and multimodal collection.