Currently, traditional feature extraction algorithms have poor data expression and noise robustness. Moreover, traditional recognition methods are gradually falling behind the demand for increasing data, and struggle to extract deep features in targets. By considering the preceding issues, an integrated neural network has been created in this paper for underwater acoustic target recognition via feature fusion learning. Firstly, the short time Fourier transform (STFT) amplitude spectrum, STFT phase spectrum, and bispectrum feature of underwater acoustic signals are extracted and form the input for the network. They not only contain rich information about the target, but also have strong noise robustness. Secondly, an integrated neural network has been designed, which is trained with different features and contains three neural networks. Finally, in the softmax layer of the network, the shuffled frog leaping algorithm (SFLA) is utilized to train the weight coefficients of different networks. Experimental results of the measured data show that the integrated neural network method based on feature fusion has a higher recognition accuracy and stronger noise robustness.

目前，传统的特征提取算法数据表达能力和噪声鲁棒性较差。此外，传统的识别方法逐渐落后于不断增长的数据需求，难以提取目标的深层特征。考虑到上述问题，本文创建了一种集成神经网络，用于通过特征融合学习进行水声目标识别。首先，提取水声信号的短时傅里叶变换（STFT）幅度谱、STFT相位谱和双谱特征，形成网络的输入。它们不仅包含丰富的目标信息，而且具有很强的噪声鲁棒性。其次，设计了一个集成神经网络，该网络经过不同特征的训练，包含三个神经网络。最后，在网络的 softmax 层，利用 shuffled 蛙跳算法（SFLA）训练不同网络的权重系数。实测数据的实验结果表明，基于特征融合的集成神经网络方法具有更高的识别准确率和更强的噪声鲁棒性。