Personal statement

Sarini Jayasinghe serves as Data Analytics Theme Lead at the National Manufacturing Institute Scotland (NMIS), where she manages a team of data scientists and engineers while overseeing data analytics projects across various manufacturing domains. Her research focuses on applying machine learning and data analytics to manufacturing processes, with expertise in predictive modeling, sensor data analysis, and digital twin development. Her career spans academia and industry, beginning with a PhD from the University of Liverpool (2018-2022) where she developed machine learning models for real-time detection of additive manufacturing build anomalies using photodiode sensor data. As a post-doctoral researcher at Liverpool, she created a machine-learnt online model for predicting furnace fault density in float glass production, implementing a 72-hour forecasting system using Gaussian process regression that was successfully deployed and recognized as the best project by Transforming Foundation Industries Network+. At NMIS, she has worked across diverse manufacturing themes including machining, additive manufacturing, forming, and forging. Notable projects include developing furnace operation models for temperature and oxygen optimization, strain prediction models for Ti6Al4V using finite element analysis data, and quality prediction systems for dimensional accuracy improvement. Her work combines advanced analytics techniques with practical manufacturing applications, contributing to digital transformation initiatives.