An Aging Small-signal Modeling Method of Microwave Transistors Using GA-ELM Neural Network

In this paper, an aging small-signal S-parameters modeling method for microwave transistors is explored using a genetic algorithm (GA) to optimize the Extreme Learning Machine (ELM) neural network. A dual GA-ELM neural network architecture was used to simulate the fresh S-parameters of InP heterojunction bipolar transistor (HBT) devices and the degradation of S-parameters after accelerated aging, respectively. Good agreement was achieved between measured and predicted results of the fresh and aging S-parameters within a frequency range of 0.1 to 40 GHz.