Abstract
Efficient and high-precision prediction of underwater vehicle radiated noise is crucial for warship stealth assessment. To overcome the high modeling complexity and limited prediction capability of traditional methods, this paper proposes ADE-PNN-ResNet, a fast underwater radiated noise (URN) prediction model integrating Adaptive Differential Evolution (ADE) with a Parallel Residual Neural Network (PNN-ResNet). This data-driven framework replaces conventional physics-based modeling, significantly reducing complexity while preserving high prediction accuracy. This study includes three core points: Firstly, for each 1/3-octave target noise band, a joint feature selection strategy of measurement points and frequency bands based on the ADE is proposed to provide high-quality inputs for the subsequent model. Secondly, a Parallel Neural Network (PNN) is constructed by integrating Radial Basis Function Neural Network (RBFNN) that excels at handling local features and Multi-Layer Perceptron (MLP) that focuses on global features. PNN is then cascaded via residual connections to form PNN-ResNet, deepening the network layers and efficiently capturing the complex nonlinear relationships between vibration and noise. Thirdly, the proposed ADE-PNN-ResNet is validated using vibration and noise data collected from lake experiments of a scaled underwater vehicle model. Under the validation conditions, the absolute prediction error is below 3 dB for 96% of the 1/3-octave bands within the frequency range of 100-2000 Hz, with the inference time for prediction taking merely a few seconds. The research demonstrates that ADE-PNN-ResNet balances prediction accuracy and efficiency, providing a feasible intelligent solution for the rapid prediction of underwater vehicle radiated noise in engineering applications.