| KEYWORD |
AA - Materials and Processes for Micro and Nano Technologies
AI Techniques for the Optimisation of Highly Integrated Power Modules
keywords DESIGN BY EXPERIMENTS, FEM SIMULATION
Reference persons SERGIO FERRERO, LUCIANO SCALTRITO
Research Groups AA - Materials and Processes for Micro and Nano Technologies
Thesis type EXPERIMENTAL AND SIMULATION
Description Electronic Integration is now considered a new paradigm for the semiconductor packaging industry to sustain Moore’s law. Vertical stacking of semiconductor chips provides high power density in a given footprint area. However, owing to increased integration, 3-D ICs having multiple core areas (hotspots) on each stack layer can often be prone to thermal interaction between the stack layers (Interlayer) and within the stack layers (Intralayer). The design of these devices must be optimised to get the lowest and most uniform temperature in the whole device. AI techniques can be employed to achieve the best performance from such devices. [1][2][3]
The thesis goal is to produce an AI algorithm to achieve the optimum configuration (parameters and geometry) of a given Power Module.
The work will be organised as follow:
• Literature review
• Write optimisation code
• Application on well-known cases
• Application on a real device
[1] Rangarajan et al., Supervised Machine-Learning Approach for the Optimal Arrangement of Active Hotspots in 3-D Integrated Circuits, 2021.
[2] Lu et al., Temperature gradient-aware thermal simulator for three-dimensional integrated circuits, 2017
[3] Joo Park et al., Application of Machine Learning for Optimization of 3-D Integrated Circuits and Systems, 2017
Required skills Good knowledge of the COMSOL tool
Deadline 08/06/2025
PROPONI LA TUA CANDIDATURA