Rapid Flow Behavior Modeling of Thermal Interface Materials Using Deep Neural Networks
This work addresses thermal management challenges in electronic packaging by enabling faster and more automated design of TIM dispensing patterns, though it is incremental as it builds on existing heuristic and ANN methods.
The authors tackled the problem of efficiently modeling the spreading behavior of Thermal Interface Materials (TIMs) for complex geometries in electronic packaging, proposing a lightweight heuristic and an Artificial Neural Network (ANN) that offers rapid computation times and gradient information for automated pattern optimization, validated with real product samples.
Thermal Interface Materials (TIMs) are widely used in electronic packaging. Increasing power density and limited assembly space pose high demands on thermal management. Large cooling surfaces need to be covered efficiently. When joining the heatsink, previously dispensed TIM spreads over the cooling surface. Recommendations on the dispensing pattern exist only for simple surface geometries such as rectangles. For more complex geometries, Computational Fluid Dynamics (CFD) simulations are used in combination with manual experiments. While CFD simulations offer a high accuracy, they involve simulation experts and are rather expensive to set up. We propose a lightweight heuristic to model the spreading behavior of TIM. We further speed up the calculation by training an Artificial Neural Network (ANN) on data from this model. This offers rapid computation times and further supplies gradient information. This ANN can not only be used to aid manual pattern design of TIM, but also enables an automated pattern optimization. We compare this approach against the state-of-the-art and use real product samples for validation.