Error correction algorithm of array time-varying amplitude and phase based on autoencoder

Abstract

As array antennas are widely used in various mobile platforms, the time-varying amplitude and phase error has become an important factor affecting the application of array signal processing technology. A deep learning-based algorithm for the correction of time-varying amplitude and phase errors in arrays is proposed in terms of the idea of autoencoder. The algorithm makes full use of the data feature extraction and reconstruction capability of the autoencoder network, designs a deep learning network for the correction of time-varying amplitude phase error of the channel, gives a double-driven learning mechanism without time-varying amplitude phase error data (unperturbed data) and time-varying amplitude phase error data (perturbed data), completes the extraction of the array stream shape hidden features based on the principle of minimising the mean square error of the desired output and the ideal model. The simulated experiments show that the algorithm can effectively correct the time-varying amplitude and phase errors of each channel, and the mean square error of the corrected amplitude and phase errors are within 0.5% and 1.5% respectively when there are ±80% random time-varying amplitude errors and ±5° random time-varying phase errors. The effectiveness of the proposed algorithm is verified.