(366d) Automating Data-Driven Methodologies for the Next Generation of Industrial Processes

My research is focused on automating tools that harness machine learning and digital twin technology to streamline their application in industry, particularly for optimization and control processes. During my Ph.D. at Politecnico di Milano, I developed an automated framework for creating surrogate models from digital twin data. This framework facilitates process optimization and control, making these advanced methods more accessible and easier to implement in industrial settings. One of the key applications of this framework was the global surrogate modeling of an industrial amine scrubbing process. Additionally, I optimized a biogas-to-methanol industrial pilot plant, which resulted in a 22% reduction in energy expenditure.

As a post-doctoral researcher at Imperial College London, I have extended my work to the biopharmaceutical industry. I developed a machine learning methodology for resin screening in Protein A chromatography, utilizing transfer learning to enhance model accuracy and reduce experimental costs. This approach combines experimental data with high-fidelity digital twins, accelerating process development and promoting sustainable manufacturing practices. My ongoing r0esearch aims to further automate and simplify these methodologies, fostering their adoption and integration into various industrial applications.

Teaching Interests

I am passionate about teaching and mentoring the next generation of chemical engineers. My teaching philosophy centers on integrating theoretical knowledge with practical applications, fostering a learning environment that encourages critical thinking and problem-solving. During my Ph.D. at Politecnico di Milano, I delivered lectures and practical sessions annually for the Master of Science course in Chemical Plants II, and I also conducted oral examinations. Additionally, I am currently a teaching assistant for the Advanced Process Design course for undergraduate students in Chemical Engineering at Imperial College London. I have mentored over 10 master’s students throughout my Ph.D. and continue to support thesis students at Imperial College. I aim to teach courses related to process optimization, machine learning applications in chemical engineering, and digital twin technology, and I am committed to developing new courses that bridge traditional chemical engineering principles with modern digital advancements.