CONTROL OF SOUND NOISE RADIATED FROM A PLATE USING DYNAMIC ABSORBERS UNDER THE OPTIMIZATION BY NEURAL NETWORK

This paper reports a system for reducing sound radiated from a plate using electromagnetic vibration absorbers. Conventional design techniques for vibration absorbers are not appropriate for sound reduction absorbers, because higher-mode vibrations exert strong effects on noise. Hence, an analytical expression for noise level including higher modes has been first derived, then a method for obtaining optimal parameters for noise reduction absorbers is presented. In this method, an integrated value of the sound pressures in a frequency domain is taken as a cost function, and the parameters are decided by using a neural network procedure. An algorithm of the neural network for obtaining the parameters is given. Numerical calculations and experimental tests are carried out for some important cases.