Research

For the past five years, a majority of my research focus has been on the development of digital twins and digitalisation of the manufacturing industry. As part of the research, I have explored concepts of using digital models for process planning, concept stage decision making and continuous improvement of processes. There is great potential in the use of digital models and incorporating them within the lifecycle of a manufacturing system. Particularly, my focus has been on the use of Discrete-Event Simulation Models to support scale-up of production systems.

The use of simulation coupled with an optimisation technique serves as a powerful tool for any manufacturing enterprise. It not only has the capability to compare different design scenarios but also provides near-optimal solutions that can can bring cost and time savings. My doctoral research focus was on the use of heterogeneous digital models, knowledge representation and optimisation to provide a decision support tool for manufacturing system designs. I am currently exploring the possibility of extending this research for production logistics.

Sustainable smart manufacturing is an interesting area of research where the concepts of Digital Twins, Smart Sensors, and Cyber-Physical Systems are explored from a sustainability angle. It provides a new dimension to smart manufacturing and aims to reduce the carbon emissions and improve the energy efficiency in manufacturing industries.

I am currently working on applied artificial intelligence where the machine learning and deep learning principles can be applied to detect, predict and localise defects in the manufacturing industry. In this context, my experience lies in classifying images using CNNs, hyperparameter optimisation, and defect localisation using RCNN.