Extended Hammerstein Behavioral Model Using Artificial Neural Networks

• Published in: IEEE transactions on microwave theory and techniques Vol. 57; no. 4; pp. 745 - 751
• Main Authors: Mkadem, F., Boumaiza, S.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.04.2009; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Amplifiers; Applied sciences; Artificial neural network (ANN); Artificial neural networks; Broadband amplifiers; Circuit properties; Code Division Multiple Access; Design. Technologies. Operation analysis. Testing; Dispersion; Dynamics; Electric, optical and optoelectronic circuits; Electronic circuits; Electronic equipment and fabrication. Passive components, printed wiring boards, connectics; Electronics; Error signals; Exact sciences and technology; Feedforward neural networks; Feedforward systems; Integrated circuits; Mathematical models; Microwave circuits, microwave integrated circuits, microwave transmission lines, submillimeter wave circuits; Microwaves; Networks; Neural networks; PA nonlinearity; power amplifier (PA) behavioral modeling; Power amplifiers; Predictive models; Radio frequency; Radiofrequency amplifiers; Semiconductor electronics. Microelectronics. Optoelectronics. Solid state devices; Wideband; Wiener/Hammerstein model; Input signal; Wiener/Hammerstein model; Artificial neural network (ANN); Memoryless circuit; Modeling; Non linear phenomenon; Wideband amplifiers; Accuracy; Feedforward neural nets; Wide band; Signal spectrum; PA nonlinearity; Optoelectronic device; Hammerstein equation; Radiofrequency amplifiers; Millimeter wave integrated circuits; Monolithic integrated circuit; power amplifier (PA) behavioral modeling; Power electronics; Output signal; Neural network; Behavior model; Light emitting diode; Code division multiple access; Power amplifier; Non linear effect; Memory effect
• ISSN: 0018-9480; 1557-9670
• DOI: 10.1109/TMTT.2009.2015092

In this paper, a novel extended Hammerstein model is presented to accurately mimic the dynamic nonlinearity of wideband RF power amplifiers (RFPAs). Starting with a conventional Hammerstein model scheme, which fails to predict the behavior of the RFPA with short-term memory effects, two areas of improvements were sought and found to allow for substantial improvement. First, a polar feed-forward neural network (FFNN) was carefully chosen to construct the memoryless part of the model. The error signal between the output and the input signal of the memoryless sub-model was then filtered and then post-injected at the model output. This extra branch, when compared to the conventional Hammerstein scheme, allowed for an extra mechanism to account for the memory effects due to dispersive biasing network that was present otherwise. The excellent estimation capability of the polar FFNN together with the additional filtered error signal post-injection led to remarkable accuracy when modeling two different RFPAs both driven with four-carrier wideband code division multiple access signals. Despite its simple topology and identification procedure, the extended Hammerstein model demonstrated is capable in accurately predicting the dynamic AM/AM and AM/PM characteristics and the output signal spectrum of the RFPA under test.