Behavior modeling for multi-carrier multi-mode power amplifiers using real-valued time-delay RBF networks

Hui, Ming; Liu, Taijun; Yan, Ye; Zhang, Haili; Shen, Dongya

doi:10.1109/icecc.2011.6067572

Cited by 8 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where X(m, n) is the mth element of X(n), and C i (m) are the centres of the RBF. β is a constant equal to sp/(−ln0.5) Performance assessment of ARBFNN-based nonlinear model: The test platform utilised is similar to that in [7]. A 51 dBm peak power DPA was used in this study for modelling and linearisation validation measurement.…”

Section: Fig 1 Block Diagram Of Arbfnn Modelmentioning

confidence: 99%

“…The test platform utilised is similar to that in [7]. A 51 dBm peak power DPA was used in this study for modelling and linearisation validation measurement.…”

Section: Performance Assessment Of Arbfnn‐based Nonlinear Modelmentioning

confidence: 99%

“…A radial basis function (RBF) NN has only one hidden layer, eliminating the need for cumbersome calculations and thus greatly reducing the training time. A real‐valued time‐delay RBF NN [7] accounts for memory effects with a time‐delay structure, and both of its input and output signals are real. However, it cannot accurately describe the strong nonlinearity of PAs.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Augmented radial basis function neural network predistorter for linearisation of wideband power amplifiers

et al. 2014

Self Cite

View full text Add to dashboard Cite

An augmented radial basis function neural network (ARBFNN) is proposed for modelling and linearising a wideband Doherty power amplifier (DPA) with strong memory effects and static nonlinearity. To evaluate the performance of the ARBFNN, a 51 dBm DPA and a 25 MHz mixed test signal were used in modelling and linearisation measurement. Compared with the memory polynomial (MP) model and the real-valued time-delay neural network (RVTDNN), the ARBFNN is highly effective, leading to 3 and 5 dB improvements in the normalised mean square error. More importantly, the ARBFNN predistorter represents a significant improvement over the RVTDNN and MP in the suppression of the out-of-band spectral regrowth. In addition, the ARBFNN has a similar linearisation capability as the generalised MP model, but has much better numerical stability.

show abstract

Section: Fig 1 Block Diagram Of Arbfnn Modelmentioning

confidence: 99%

“…The test platform utilised is similar to that in [7]. A 51 dBm peak power DPA was used in this study for modelling and linearisation validation measurement.…”

Section: Performance Assessment Of Arbfnn‐based Nonlinear Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation