Evaluation of the Applicability of Neural Networks to Suppress Harmonic Distortion of HF Power Amplifiers

Pavlov, A. P.; Kashchenko, I. E.; Krivaltsevich, S. V.

doi:10.1109/weconf.2019.8840597

Cited by 5 publications

(7 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature, there have been some digital filter‐less architectures proposed for harmonic cancelation. These architectures can be roughly divided into three categories: Baseband harmonic injection techniques 9,10 . The harmonics were captured and modeled with polynomial models in Reference 9.…”

Section: Introductionmentioning

confidence: 99%

A low‐spur harmonic‐cancelation digital predistortion based on neural network for frequency‐hopping HF transmitters

Chen

et al. 2023

Int J Numerical Modelling

View full text Add to dashboard Cite

High frequency (HF) transmitter implemented with the multioctave broadband power amplifier (PA) is always faced with the problem of interfering harmonics because of the nonlinearity of the PA. With the harmonic‐cancelation digital predistortion (HC‐DPD) scheme, the harmonics at lower frequencies can be canceled by the injected components and the harmonics at higher frequencies can be filtered out using a low‐pass filter (LPF). However, the HC‐DPD scheme brings the problem of unwanted spurs while lowering the requirements for sampling rate. In this article, a time‐delay neural network (TDNN) model is used to replace the conventional memory polynomial (MP) model in the forward modeling. Theoretical derivation and simulation results validate the effectiveness of the TDNN model in harmonic cancelation and spur suppression. Further, a frequency‐agile neural network (FANN) model is proposed based on the TDNN model. By adding the carrier frequency to the inputs of the network, the trained model can apply to all the trained carrier frequencies and is more friendly to the frequency‐hopping scenarios. Experiments were carried out on a 2–30 MHz HF transmitter testbench. Measurement results show that the harmonic‐to‐fundamental power ratio, the adjacent channel power ratio (ACPR), and the error vector magnitude (EVM) performances were all improved by more than 20 dB. Compared with the MP model, the unwanted spurs can be suppressed by up to 22 dB. In addition, the number of total model coefficients of the proposed FANN model is only 22% of that of the TDNN model under the frequency‐hopping scenario.

show abstract

Section: Introductionmentioning

confidence: 99%

A low‐spur harmonic‐cancelation digital predistortion based on neural network for frequency‐hopping HF transmitters

Chen

et al. 2023

Int J Numerical Modelling

View full text Add to dashboard Cite

show abstract

“…In the literature, there have been some investigations on filter‐less architectures for harmonic cancelation. These architectures can be roughly divided into three categories: Baseband harmonic injection techniques 19,20 . The harmonics were captured and modeled with polynomial models in Reference 19.…”

Section: Introductionmentioning

confidence: 99%

“…The baseband harmonic injection signals were transmitted with additional channels. In addition, 20 adopted a neural network (NN) to adapt the phase of the injected signal. Feed‐forward harmonic cancelation techniques 21–23 . The DPD was used to mitigate the IMD and the harmonics were injected after the linear error amplifier and hybrid coupler.…”

Section: Introductionmentioning

confidence: 99%

“…Baseband harmonic injection techniques. 19,20 The harmonics were captured and modeled with polynomial models in Reference 19. The baseband harmonic injection signals were transmitted with additional channels.…”

Section: Introductionmentioning

confidence: 99%

“…The baseband harmonic injection signals were transmitted with additional channels. In addition, 20 adopted a neural network (NN) to adapt the phase of the injected signal. 2.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Nonlinear modeling and digital predistortion for HF transmitters with harmonic cancelation

Chen

et al. 2022

Int J Numerical Modelling

View full text Add to dashboard Cite

High frequency (HF) transmitters implemented with the multi-octave power amplifier (PA) are always faced with the problem of interfering harmonics because of the nonlinearity of the PA. In this paper, the harmonic cancelation digital predistortion (HC-DPD) scheme is proposed and well discussed to cancel the in-band intermodulation distortion (IMD) as well as out-of-band harmonics at the same time. With the digital filter-less scheme, the bulky and lossy filter banks can be removed. Nonlinear models are first utilized to approximate the nonlinear behavior of the HF PA and compared in terms of the model accuracy. Then, the learning architecture, model identification, and feedback compensation of the HC-DPD scheme are detailed discussed. Finally, a series of simulations and experiments demonstrated the effectiveness of the proposed nonlinear models and linearization algorithms.

show abstract

Application of Neural Networks to Reduce Distortion of RF Signals in Switch Mode Power Amplifiers

Sorotsky

Zudov

2020

2020 IEEE International Conference on Electrical Engineering and Photonics (EExPolytech)

View full text Add to dashboard Cite

Evaluation of the Applicability of Neural Networks to Suppress Harmonic Distortion of HF Power Amplifiers

Cited by 5 publications

References 2 publications

A low‐spur harmonic‐cancelation digital predistortion based on neural network for frequency‐hopping HF transmitters

A low‐spur harmonic‐cancelation digital predistortion based on neural network for frequency‐hopping HF transmitters

Nonlinear modeling and digital predistortion for HF transmitters with harmonic cancelation

Application of Neural Networks to Reduce Distortion of RF Signals in Switch Mode Power Amplifiers

Contact Info

Product

Resources

About