Skip to content

Τhis work demostrates the potential of digital twins in the industry as well as how they can be simulated and trained with A.I. methods. Digital twin modeling does not necessarily need tools from data science or machine learning. However, it is prudent to use such modeling techniques wherever applicable and suitable.

Notifications You must be signed in to change notification settings

henri-xh/Diploma-Thesis

Repository files navigation

Diploma-Thesis

Τhis work demostrates the potential of digital twins in the industry as well as how they can be simulated and trained with A.I. methods. Digital twin modeling does not necessarily need tools from data science or machine learning. However, it is prudent to use such modeling techniques wherever applicable and suitable. In our case we will make a digital twin of a MOSFET and later on we will use Deep Learning models on it. The target of this work is that by creating the digital twin, it can allows you to swap out an analytical model with an Machine Learning model (and vice versa).

More precisely, with using an ML technique, we are going to predict the Sub-Threshold leakage of a MOSFET, a phenomenon found in all MOSFETs. Later on, it is going to get discussed with more details.

About

Τhis work demostrates the potential of digital twins in the industry as well as how they can be simulated and trained with A.I. methods. Digital twin modeling does not necessarily need tools from data science or machine learning. However, it is prudent to use such modeling techniques wherever applicable and suitable.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published