One of the commonly used 3D printing methods is material extrusion, owing to its ease of use and wide availability of materials. However, this method faces two critical challenges to achieve desired results in products. They include optimisation of processing parameters and unexpected maintenance. This results in a trial-and-error approach, leading to wastage of significant amount of time and resources. To overcome such challenges, digital twins have become exceedingly popular as they enable manufacturers to optimize parameters, detect faults, and assess performance before physical production, reducing waste, minimizing downtime, and accelerating decision-making. However, developing a digital twin requires navigating the complexities inherent in manufacturing processes and handling substantial datasets, necessitating the utilization of sophisticated modelling techniques and artificial intelligence. This talk analyses the feasibility of applying a digital twin with artificial intelligence to predict the behaviour of the material extrusion 3D printing process. By leveraging artificial intelligence in tandem with digital twin technology, new insights could be unlocked, propelling the manufacturing sector towards greater innovation and competitiveness.