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. Simulations of the new system and the FM removal algorithm, which take the rotational speeds of the blower as reference signals and also actual noise as primary signals, have been carried out respectively and compared afterwards. The simulation results demonstrate that the proposed system far outperforms the FM removal algorithm at high frequencies. The former is capable of tracking frequency of non-stationary or time-varying input signals and further removing FM, and its noise reductions generally reach approximately 20 dB, while the latter reduces less than 2 dB. Additionally the new system proves to be effective and efficient even though the FM reaches 250 Hz.