Artificial Neural Network Model of SOS-MOSFETs Based on Dynamic Large-Signal Measurements

• Published in: IEEE transactions on microwave theory and techniques Vol. 62; no. 3; pp. 491 - 501
• Main Authors: Youngseo Ko, Roblin, Patrick, Zarate-de Landa, Andres, Apolinar Reynoso-Hernandez, J., Nobbe, Dan, Olson, Chris, Martinez, Francisco Javier
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.03.2014; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applied sciences; Artificial intelligence; Artificial neural network (ANN); Artificial neural networks; Computer science; control theory; systems; Connectionism. Neural networks; Control theory. Systems; Current measurement; Data models; Electronics; Exact sciences and technology; large-signal network analyzer (LSNA); Load modeling; Logic gates; memory effects; Modelling and identification; MOSFET; Neural networks; parasitic bipolar junction transistor (P-BJT); Radio frequency; real-time active load-pull (RTALP); Semiconductor electronics. Microelectronics. Optoelectronics. Solid state devices; Testing, measurement, noise and reliability; Transistors; Voltage measurement; MOSFET; Voltage current curve; parasitic bipolar junction transistor (P-BJT); Artificial neural network (ANN); Modeling; Load impedance; real-time active load-pull (RTALP); Dynamic measurement; Active system; Network analysis; Voltage; Bipolar technology; System identification; MOS technology; Insulated gate bipolar transistor; Quasi static theory; Coverage; Neural network; Topology; Real time; Bipolar transistor; Field effect transistor; memory effects; Data models; Non linear effect; Memory effect; large-signal network analyzer (LSNA)
• ISSN: 0018-9480; 1557-9670
• DOI: 10.1109/TMTT.2014.2298372

A measurement-based quasi-static nonlinear field-effect transistor (FET) model relying on an artificial neural network (ANN) approach and using real-time active load-pull (RTALP) measurement data for the model extraction is presented for an SOS-MOSFET. The efficient phase sweeping of the RTALP drastically reduces the number of large-signal measurements needed for the model development and verification while maintaining the same intrinsic voltage coverage as in conventional passive or active load-pull systems. Memory effects associated with the parasitic bipolar junction transistor (BJT) in the SOS-MOSFET are accounted for by using a physical circuit topology together with the simultaneous ANN extraction of: 1) the intrinsic FET current-voltage characteristics; 2) the intrinsic charges of the FET; and 3) the BJT dc characteristics, all from the same modulated large-signal RF data. The verification of the model using load-lines, output power, power efficiency, and load-pull, which is performed using two additional independent RTALP measurements, demonstrates that a reasonably accurate large-signal RF device model accounting for memory effects can be extracted from a single 10.5-ms RTALP measurement with a physically based ANN model.