Search Results

In order to reduce high-frequency harmonic noise produced by the blower in the auxiliary system of a fuel cell vehicle (FCV), a narrowband active noise control (ANC) method instead of conventional passive mufflers is adopted since the blower demands clean air condition and expects good acoustic performance. However, in ANC practical applications, the frequency difference between reference signal and actual primary signal, i.e., frequency mismatch (FM), can significantly degrade the high-frequency performance of narrowband ANC system. In this paper, a new narrowband ANC system is proposed to compensate for the performance degeneration due to the existence of FM and improve noise reduction at high frequencies. The proposed system consists of two parts: the Filtered Error Least Mean Square (FELMS) algorithm filtering the primary signals at wide frequency range other than those at the targeted frequencies, and the FM removal algorithm proposed by Yegui Xiao.

In this paper, the system identification theory and method using dynamic neural networks are presented, the multilayer feedforward networks employed, the backpropagation with adaptive learning rate algorithms proposed. Finally the comparision of network output with that of the hydrostatic drive system of secondary regulation is given, and output error, sum-squared error et al, or the results that embody the effect of system identification given sine input to it are provided.