Prediction of muffler flow regeneration noise with neural network

Flow regeneration noise is a main reason effect on attenuation performance of mufflers, at present no sophisticated software or tool is found to predict effectively flow regeneration noises from mufflers. Prediction of flow regeneration noise from a muffler element of simple expansion chamber is realized using Bp neural network, and comparison of prediction with experiment is carried out. Results show that they agree well, forecasting precision is high, and that fuzzy normal establishment program work is avoided. Significant foundation is provided for researching on production mechanism of flow regeneration noise from mufflers and improving attenuation performance.