Prediction of sound insulation performance of aramid honeycomb sandwich panel based on artificial neural network

•The artificial neural network method is used to quickly predict the sound insulation performance of aramid honeycomb sandwich panel.•Backpropagation neural network are unable to predict the local characteristics of sound insulation performance.•Radial basis function neural network has over fitting in the case of less training data.•The general region neural network has the best prediction effect, with a prediction error of 3.45%throughout the whole frequency range.