Signals Recognition of Underwater Acoustic Communication based on Artificial Neural Network and Signal Feature Extraction

Abstract

Modulation pattern recognition is an important part of underwater acoustic communication. Due to the complexity of underwater acoustic media (propagation loss, ocean noise, multipath effect and Doppler effect), underwater acoustic channel is considered to be one of the most challenging wireless communication channels. This paper proposed an intelligent underwater acoustic signal processing and recognition method based on artificial neural network (ANN) and signal feature extraction. Firstly, the real part and imaginary part of the signal are extracted by fast Fourier transform (FFT), the variance, mean and other eigenvalues of the real part and imaginary part are calculated, respectively. Secondly, the extracted signal features are used to train ANN classifier to realize the classification and recognition of different signals. In this way, the intelligent recognition of underwater acoustic signal by data-driven method is realized. Finally, the effectiveness of the proposed method is verified by simulation, and the good recognition effect is achieved.