Research and optimization of noise and sound quality of tailpipe of automobile exhaust system
Aiming at the problem of tailpipe noise and sound quality of a certain type of automobile exhaust system,a radial basis function(RBF)neural network is proposed to establish an exhaust system structure-tailpipe noise quality prediction model,and optimize the noise and sound quality of exhaust system through adaptive simulated annealing algorithm to improve the sound quality of exhaust system.Taking a certain type of automobile exhaust system as the research object,a sample database containing structural parameters was established,and the noise data of the sample data obtained were obtained by simulation calculation with GT-POWER,and the subjective evaluation of the sound quality of the simulated sound data were scored,and the exhaust system structure-tailpipe noise quality prediction model was established by the RBF neural network,and the contribution and main effects of the exhaust system structural parameters as model independent variables to the tailpipe noise quality were analyzed.Finally,the adaptive simulated annealing algorithm is used to optimize the structural parameters of the exhaust system,the optimization results are verified experimentally,and the results show that the sound quality of the exhaust system is significantly improved.
NETL
NSTL
万方数据
