About
Emmanuel Akeweje
Postgraduate Researcher
TCD
Emmanuel Akeweje is a PhD researcher at I-Form, Trinity College Dublin, with a specialization in Statistics. He holds a Master’s degree in Data Science from the Skolkovo Institute of Science and Technology, Russia, and another in Mathematical Sciences from the African Institute for Mathematical Sciences, Ghana, where his thesis focused on modeling the dynamics and stability of femtosecond laser inscription in transparent materials. He also earned a Bachelor’s degree in Mathematics from the Federal University of Agriculture, Abeokuta, Nigeria. With a diverse research portfolio spanning theoretical mathematical modeling and applied machine learning, Emmanuel is passionate about leveraging his expertise to create innovative and impactful solutions across various sectors.
Technical Summary
My research focuses on harnessing artificial intelligence (AI) to transform experimental design in additive manufacturing (AM), moving away from inefficient trial-and-error methods. The inherently dynamic nature of AM, where multiple factors interact during the 3D printing process, makes real-time adjustments essential for producing high-quality and cost-effective products. By incorporating multi-modal data - combining multivariate measurements such as temperature, pressure, material properties, and laser speed with time-series data that tracks these variables throughout the printing process and image data that monitors shape, texture, and structural integrity in real time - I aim to create AI systems that optimize experimental designs and adapt dynamically as new information becomes available.
This approach addresses critical challenges in AM, particularly in multi-objective optimization, where manufacturers must balance competing goals like strength, durability, weight, and cost. By improving efficiency, reducing waste, and enabling real-time decision-making, AI-driven experimental design has the potential to significantly streamline AM processes while enhancing the quality of printed components. The ability to make real-time adjustments ensures that every part meets stringent industry standards, particularly in sectors such as aerospace and healthcare.
I am also developing machine learning models to predict the mechanical properties of printed products using real-time data collected during the printing process. These predictive models enable immediate adjustments to key parameters like laser speed or material feed rate, ensuring final products align with desired specifications.