71 / 2023-08-31 22:52:56

A Prior Knowledge-Based Neural Network Model for Degradation Prediction of Microwave HBT S-parameters

S-parameters,degradation,prior knowledge,extreme learning machine

Special Sessions > SS06 - Artificial Intelligence for Semiconductor Modelling and Applications

In this paper, a prior knowledge neural network (PKNN)-based modeling approach for degradation prediction of microwave HBT S-parameters is explored. In addition to the reliability parametric inputs of the original aging problem, the Sparameter degradation trend obtained from the aging small-signal equivalent circuit is used as an additional information to inject into the extreme learning machine structure. Good agreement was achieved between measured and predicted results of the degradation of S-parameters within a frequency range of 0.1 to 40 GHz.