Thermal performance of PBGA package using Artificial neural network

This paper investigates the thermal performance of Plastic Ball Grid Array (PBGA) using Artificial Neural Network. In this paper, the feed-forward backpropagation network is applied to the PBGA model. Results from Finite Element Method are used to train the neural network. The resulting artificial neural network model was then used to estimate the value of junction temperature (T J ) for the PBGA package. It is found that the neural network provides a fast solutions for PBGA once the network is trained, thus eliminating further calculations using the computation intensive FEM.