A modified model, in the form of an FIR filter, is proposed for the mo
delling of the acoustic dynamics of an active noise control system. Th
is is a low order filter formulation but consists of two independent e
lements-a time delay and a d.c. gain Empirical data has shown that thi
s model constitutes a good representation of the equivalent high order
FIR filter and has the additional feature of being a high frequency n
oise filtering device. Because of its specific structure, the time del
ay and gain must be identified independently. This restricts the use o
f the conventional least mean squares technique for parameter optimiza
tion, as the cost function intrinsically comprises multimodal error su
rfaces. The use of Genetic Algorithms could be the best solution to ad
dress this issue but their unpredictable response in real-time require
some special attention. A fully developed active noise control system
, based on the Genetic Algorithm, to achieve the objective of noise re
duction is described. To further guarantee the reliability of this app
roach, a supervisory scheme is incorporated for governing the real-tim
e learning operations. A parallel hardware architecture, using two ind
ependent TMS320C30 digital signal processors, is designed for such imp
lementation. The experimental results indicate that this approach to n
oise control is sound, and that noise reduction of more than 15dB(A) i
s consistently obtained.