Optimization of Secondary Path Identification in Active Noise Control Based on Neural Network
-
摘要: 针对有源噪声控制中非线性因素影响建模精度和控制效果的问题，采用神经网络代替传统模型，推导对应的控制算法。用训练结果验证了神经网络对次级通道辨识模型精度的提高。以管道为实验对象，搭建有源噪声控制实验平台，进行噪声控制实验，将传统次级通道模型与优化次级通道模型的实验结果进行对比。结论表明：在低频条件下，针对单一频率和两种频率混合的噪声源，相比传统模型和算法，神经网络优化模型和算法取得了较好的效果。Abstract: Noise is an important problem which need to be resolved in people's life. The modeling accuracy and control result in active noise control are affected by the nonlinear factors. Secondary path identification is optimized according to the active noise control (ANC) principle, to improve the accuracy and effect of noise control. The finite impulse response (FIR) model used to identify is replaced by the back propagation (BP) neural network, which performs better on the nonlinear factors. Based on least mean square (LMS) algorithm, the ANC algorithm under the secondary path model of neural network is deduced, and the iteration formula of coefficients is derived. The active noise control platform in a duct is built with the TMS320VC5509A as the core processor and the duct as the noise environment. The platform includes input, output and processing modules. The neural network model is trained with input and output signals as training samples. The signals of secondary path are generated by the addictive white noise. The neural network improves the accuracy of secondary path identification model as shown in the training results, which means that the nonlinear factors of secondary path can be described by the neural network. The coefficients computed offline are loaded into the DSP and taken as the filtering parameters of the input signals. Under 500 Hz and 500+800 Hz noise source, the noise control experiment of FIR secondary path model and traditional ANC algorithm is compared with neural network model and optimized ANC algorithm. The results show that the algorithm is effective with good performance under the low-frequency noise of single and two-mixed frequency.
-
Key words:
- active noise control /
- nonlinear /
- secondary path /
- optimization /
- neural network
-
图 3 附加白噪声法的次级通道辨识
Figure 3. Diagram of secondary path identification based on additive white noise
图 5 神经网络次级通道辨识结构图
Figure 5. Structure of secondary path identification based on neural network
图 13 500 Hz噪声源的模拟滤波器系数
Figure 13. Simulated coefficients of the filter with 500 Hz noise
-
[1] KUO S M, MORGAN D R. Active noise control: A tutorial review[J]. Proceedings of the IEEE, 1999, 87(6): 943-973. doi: 10.1109/5.763310 [2] 陈克安. 有源噪声控制[M]. 北京: 国防工业出版社, 2003. [3] KAJIKAWA Y, GAN W S, KUO S M. Recent advances on active noise control: open issues and innovative applications[J]. Apsipa Transactions on Signal & Information Processing, 2012, 1: e3. [4] LEUG P. Process of silencing sound oscillations: US, US2043416[P]. 1936. [5] GEORGE N V, PANDA G. Advances in active noise control: A survey, with emphasis on recent nonlinear techniques[J]. Signal Processing, 2013, 93(2): 363-377. doi: 10.1016/j.sigpro.2012.08.013 [6] 关碧华, 周雅莉, 尹建民, 等. 噪声有源控制的模糊神经网络方法[J]. 北京机械工业学院学报, 2002(3): 11-14. doi: 10.3969/j.issn.1674-6864.2002.03.003 [7] ZHANG X, REN X, NA J, et al. Adaptive nonlinear neuro-controller with an integrated evaluation algorithm for nonlinear active noise systems[J]. Journal of Sound & Vibration, 2010, 329(24): 5005-5016. [8] GEORGE N V, PANDA G. A particle-swarm-optimization-based decentralized nonlinear active noise control system[J]. IEEE Transactions on Instrumentation & Measurement, 2012, 61(12): 3378-3386. [9] DAS D P, MOREAU D J, CAZZOLATO B S. Adjoint nonlinear active noise control algorithm for virtual microphone[J]. Mechanical Systems & Signal Processing, 2012, 27(2): 743-754. [10] ZHAO H, ZENG X, ZHANG X, et al. Adaptive extended pipelined second-order volterra filter for nonlinear active noise controller[J]. IEEE Transactions on Audio Speech & Language Processing, 2012, 20(4): 1394-1399. [11] LU L, ZHAO H. Adaptive volterra filter with continuous lp-norm using a logarithmic cost for nonlinear active noise control[J]. Journal of Sound & Vibration, 2016, 364: 14-29. [12] MORGAN D. An analysis of multiple correlation cancellation loops with a filter in the auxiliary path[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 2003, 28(4): 454-467. [13] BURGESS J C. Active adaptive sound control in a duct: A computer simulation[J]. The Journal of the Acoustical Society of America, 1998, 70(3): 715-726. [14] WIDROW B, GLOVER J R, MCCOOL J M, et al. Adaptive noise cancelling: principles and applications[J]. Proceedings of the IEEE, 1976, 63(12): 1692-1716. [15] ERIKSSON L J, ALLIE M C. Use of random noise for on-line transducer modeling in an adaptive active attenuation system[J]. The Journal of the Acoustical Society of America, 1989, 85(2): 797-802. doi: 10.1121/1.397552 [16] HAGAN M T, DEMUTH H B, BEALE M H. Neural network design[M]. 北京: 机械工业出版社, 2002. [17] 韩力群. 人工神经网络理论、设计及应用[M]. 北京: 化学工业出版社, 2002. [18] 陈克安, 马远良. 自适应有源消声与滤波—XLMS算法及实现[J]. 应用声学, 1993(4): 27-33. doi: 10.11684/j.issn.1000-310X.1993.04.006 -
下载:
点击查看大图
图(19)
计量
- 文章访问数: 316
- HTML全文浏览量: 227
- PDF下载量: 3
- 被引次数: 0
