基于自适应混合结构的快速收敛函数链接人工神经网络算法研究

李欢欢

振动与冲击 ›› 2021, Vol. 40 ›› Issue (10) : 180-186.

PDF(2324 KB)
PDF(2324 KB)
振动与冲击 ›› 2021, Vol. 40 ›› Issue (10) : 180-186.
论文

基于自适应混合结构的快速收敛函数链接人工神经网络算法研究

  • 李欢欢
作者信息 +

Fast convergence FLANN algorithm based on an adaptive mixing structure

  • LI Huanhuan
Author information +
文章历史 +

摘要

在非线性主动噪声控制方法中,函数链接人工神经网络(FLANN)算法是最常用的算法之一。FLANN降噪量大,但是其收敛速度较慢。为解决该问题,通过一个自适应混合参数对BFXLMS算法和FLANN算法进行有效结合,提出了CBFLANN算法。在不降低FLANN降噪量的情况下,提高了其收敛速度,解决了FLANN算法无法同时实现快速收敛和低稳态误差的问题。多个仿真实验对提出的CBFLANN算法的降噪性能进行了验证,结果表明,CBFLANN同时拥有BFXLMS的收敛速度和FLANN的降噪量。该算法的提出可以为传统主动噪声控制算法难以同时兼顾收敛速度与稳态误差的问题提供解决方案,具有很强的实际应用价值。

Abstract


Among the nonlinear active noise control methods, the functional link artificial neural network (FLANN) algorithm is one of the most commonly used algorithms.The FLANN has a better noise reduction result, but its convergence speed is slow.In order to solve this problem, a new combined bilinear FLANN (CBFLANN) algorithm by combining the bilinear filtered-x LMS (BFXLMS) algorithm with the FLANN algorithm using an adaptive mixing parameter was proposed.Without decreasing the noise reduction capability of FLANN, the convergence speed of FLANN was improved, such that the fast convergence and low steady-state error for the FLANN were achieved at the same time.To verify the performance of the proposed CBFLANN algorithm, several simulation experiments were conducted.The results show that the CBFLANN has both the convergence rate of BFXLMS and the steady-state error of FLANN at the same time.The proposed algorithm can provide a solution to the difficulty in considering both the convergence rate and the steady-state error for the conventional active noise control algorithms.It has a strong practical application value.

关键词

非线性主动噪声控制 / 函数链接人工神经网络(FLANN) / 收敛速度 / 稳态误差

Key words

nonlinear active noise control / functional link artificial neural network (FLANN) / convergence rate / steady-state error

引用本文

导出引用
李欢欢. 基于自适应混合结构的快速收敛函数链接人工神经网络算法研究[J]. 振动与冲击, 2021, 40(10): 180-186
LI Huanhuan. Fast convergence FLANN algorithm based on an adaptive mixing structure[J]. Journal of Vibration and Shock, 2021, 40(10): 180-186

参考文献

[1]杨曦, 赵华, 温妮热, 等.军事噪声性耳聋的分子流行病学研究进展 [J].西北国防医学杂志, 2015, 36(8): 535-538.
YANG Xi, ZHAO Hua, WEN Nire, et al.Advances in molecular epidemiology of military noise-induced deafness [J].Medical Journal of National Defending Forces in Northwest China, 2015, 36(8): 535-538.
[2]NUNEZ IJC, MIRANDA J G O, DUARTE M V.Active noise control in acoustic shutters [J].Applied Acoustics, 2019, 152(9): 41-46.
[3]CHANG C Y, SISWANTO A, YEH C Y, et al.Listening in a noisy environment: integration of active noise control in audio products [J].IEEE Consumer Electronics Magazine,2016, 5(4): 34-43.
[4]WU L F, QIU X J, GUO Y C.A generalized leaky FxLMS algorithm for tuning the waterbed effect of feedback active noise control systems [J].Mechanical Systems and Signal Processing, 2018, 106(3): 13-23.
[5]ZHAO T, LIANG J B, ZOU L, et al.A new FXLMS algorithm with offline and online secondary-path modeling scheme for active noise control of power transformers [J].IEEE Transactions on Industrial Electronics,2017, 64(8): 6432-6442.
[6]STRAUCH P, MULGREW B.Active control of nonlinear noise processes in a linear duct [J].IEEE Transactions on Signal Processing, 1998, 46(9): 2404-2412.
[7]CHEN B, YU S Y, YU Y, et al.Nonlinear active noise control system based on correlated EMD and Chebyshev filter [J].Mechanical Systems and Signal Processing,2019, 130(9): 74-86.
[8]罗磊,孙金玮,黄博妍,等.一种应对窄带非线性主动噪声控制的混合结构[J].电子学报, 2017, 45(8): 1801-1809.
LUO Lei, SUN Jinwei, HUANG Boyan, et al.A novel hybrid structure for narrowband nonlinear active noise control [J].Acta Electronica Sinica, 2017, 45(8): 1801-1809.
[9]LUO L, BAI Z L, ZHU W H, et al.Improved functional link artificial neural network filters for nonlinear active noise control [J].Applied Acoustics,2018, 135(6): 111-123.
[10]LE D C, ZHANG J S, LI D F.Hierarchical partial update generalized functional link artificial neural network filter for nonlinear active noise control [J].Digital Signal Processing, 2019, 93(10): 160-171.
[11]ZHAO H Q, ZENG X P, HE Z Y, et al.Improved functional link artificial neural network via convex combination for nonlinear active noise control [J].Applied Soft Computing,2016, 42(5): 351-359.
[12]LE D C, ZHANG J, LI D, et al.A generalized exponential functional link artificial neural networks filter with channel-reduced diagonal structure for nonlinear active noise control [J].Applied Acoustics,2018, 139(10): 174-181.
[13]GUO X N, LI Y, JIANG J, et al.Sparse modeling of nonlinear secondary path for nonlinear active noise control [J].IEEE Transactions on Instrumentation and Measurement, 2018, 67(3): 482-496.
[14]LU L, ZHAO H Q.Adaptive Volterra filter with continuous lp-norm using a logarithmic cost for nonlinear active noise control [J].Journal of Sound and Vibration, 2016, 364(3): 14-29.
[15]LUO L, SUN J W.A novel bilinear functional link neural network filter for nonlinear active noise control [J].Applied Soft Computing Journal,2018, 68(7): 636-650.
[16]ZHU L P, YANG T J, PAN J, et al.Reweighted adaptive bilinear filters for an active noise control system with a nonlinear secondary path [J].Applied Acoustics, 2019, 155(11): 123-129.
[17]LI T, CHEN D, DU S D.On implementation of adaptive bilinear filters for nonlinear active noise control [J].Applied Acoustics, 2016, 106(11): 122-108.

基金

Fast convergence FLANN algorithm based on an adaptive mixing structure

PDF(2324 KB)

Accesses

Citation

Detail

段落导航
相关文章

/