Chen Lequn

Chen Lequn

Research Scientist at A*STAR Advanced Remanufacturing and Technology Centre (ARTC), Singapore

A*STAR Scholar | Nanyang Technological University.

About me

I am currently serving as a Research Scientist at the Advanced Remanufacturing and Technology Centre (ARTC), at Agency for Science, Technology and Research (ASTAR), Singapore. I’m also a Ph.D. candidate (expected to graduate in Aug 2024) from the School of Mechanical and Aerospace Engineering at Nanyang Technological University (NTU), where I was honored to be co-advised by Associate Professor Moon Seung Ki (NTU, MAE), Dr. Chew Youxiang (A*STAR, ARTC) and Dr. Liu Kui (A*STAR, ARTC) and Dr. Yao Xiling (A*STAR, SIMTech, currently at NRF, Singapore). Prior to my doctoral studies, I obtained my B.Eng with the highest distinction in Mechanical Engineering from NTU in 2021.

My research is centered on advancing machine learning applications in Additive Manufacturing (AM), particularly focusing on in-situ process monitoring and defect detection through multi-sensor data fusion and robotic toolpath planning for Directed Energy Deposition (DED). My Ph.D. research developed a multi-sensor fusion-based digital twin framework aimed at real-time defect detection in L-DED. This involved the development of a monitoring system that integrates vision, acoustic, and thermal sensors, along with laser line scanners, tailored specifically for a hybrid robotic L-DED process. In addition, I also developed a data-driven adaptive control method that dynamically modulates laser power to enhance the quality of as-printed parts. My ongoing research explores several new areas:

  1. Acoustic and Thermal-based Process Control in LW-DED: This research focuses on developing adaptive process control methods for laser-wire directed energy deposition, optimizing process parameters adaptively to prevent/mitigate defect occurances.
  2. Proactive Defect Forecasting for Enhanced Quality Control: This research aims to identify potential defects at an early stage and forecast defect occurrences in LDED of complex geometries, enabling the implementation of adaptive control measures to improve part quality.
  3. Robotic Toolpath Generation: This research aims to develop advanced toolpath generation algorithms for Wire Arc Additive Manufacturing (WAAM) of large-scale marine propellers, aimed at improving production efficiency and reduced material waste.
  4. Novel Alloy Composition Design: This research focuses on utilizing machine learning-assisted surrogate modeling and multi-objective optimization to develop new Fe-Ni-Ti-Al maraging steels, leveraging CALPHAD (Calculation of Phase Diagrams) simulation techniques.