Vigneashwara
Solai Raja Pandiyan
Contact
Areas of expertise
Biography
Vigneashwara Pandiyan is a researcher at the intersection of Smart Manufacturing, Triboinformatics, and Process Monitoring. He earned his PhD from Nanyang Technological University (NTU), Singapore, where he was affiliated with the Rolls-Royce @ NTU Corporate Lab, researching Machine learning-driven process monitoring and optimization in manufacturing. Over the course of his career, Dr. Pandiyan has held research positions at Empa ETH – Swiss Federal Laboratories for Materials Science and Technology in Switzerland and the Advanced Remanufacturing and Technology Centre (ARTC) under A*STAR in Singapore. In these roles, he has investigated diverse aspects of manufacturing, ranging from laser-material interactions and metal additive processes to surface finishing, tribological wear, and streaming analytics for industrial applications. Dr. Pandiyan's research emphasizes in situ process monitoring, harnessing acoustic and optical signals (phonons and photons) to decode the fundamental physics driving material transformations in laser-based and contact-driven processes. By integrating high-fidelity optical, acoustic, and thermal sensing modalities with data-driven methodologies such as physics-informed machine learning and hybrid modelling, he develops real time diagnostic frameworks for anomaly detection and predictive modelling. Beyond his research, Dr. Pandiyan has collaborated with major academic and industrial organizations, including EPFL, ETH Zurich, KU Leuven, PSI, SimTech, Fraunhofer ILT, AC²T, Rolls-Royce, SAESL, Bystronic, Synova, and Nestlé.
Teaching
- KTEK0070 (Machine Learning in Digital Manufacturing)
- KTEK0033 (Materials Processing Technologies in Digital Manufacturing)
- KTEK0068 (Welded Metal Structures)
- KTEK0035 (Advanced Surface and Coating Technology)
- ÅAU NM00CW34 (Additive Manufacturing with Bio-based Materials and Biopolymers)
Research
- Understanding laser-material interactions for process monitoring and process control.
- Studying material transformations caused by surface contacts.
- Prognostics and pattern recognition (triboinformatics) on ageing tribological contacts.
- Developing physics-informed and data-driven machine learning approaches to model process–structure–property relationships.
- Enabling early fault detection, predictive maintenance, and improved reliability in industrial manufacturing environments.