Silicon field effect transistor radio frequency switch harmonic prediction method based on dynamic space mapping

• Main Authors: ZHOU JIEFENG, YANG SICHEN, LI ERPING, WU CHENGHAN
• Format: Patent
• Language: Chinese; English
• Published: 31.12.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a silicon field effect transistor radio frequency switch harmonic prediction method based on dynamic space mapping. A nonlinear capacitance equivalent circuit of the radio frequency switch is established as a rough model; an input signal and an output signal thereof are obtained through harmonic balance simulation, a time domain dynamic neural network is established, and a prediction network is obtained through training of the signals obtained through harmonic balance simulation; and an input signal and an output signal of the input signal are actually tested, a fine model is established through a prediction network, the signal obtained through actual testing is used for training, and harmonic prediction is achieved through the trained fine model. According to the method, the advantages of high precision of a fine model and high speed of a coarse model are combined, any capacitance effect and non-quasi-static effect missing in static neural space mapping are predicted, and harmonic wav