|Shock and Vibration||Volume 2017 ,2017-01-26|
|Wavelet Denoising of Vehicle Platform Vibration Signal Based on Threshold Neural Network|
|Mingzhu Li 1 , 2 Zhiqian Wang 1 Jun Luo 1 , 2 Yusheng Liu 1 , 2 Sheng Cai 1|
|Received 2016-06-27, accepted for publication 2016-12-20, Published 2016-12-20|
Vehicle Platform Vibration Signal (VPVS) denoising is essential to achieve high measurement accuracy of precise optical measuring instrument (POMI). A method to denoise the VPVS is proposed based on the wavelet coefficients thresholding and threshold neural network (TNN). According to the characteristics of VPVS, a novel thresholding function is constructed, and then its optimized threshold is selected through unsupervised learning of TNN. The original VPVS mixed in trend and random noise is constructed as VPVS model. A VPVS denoising flow is proposed based on the power spectral and energy distribution of the VPVS model. The simulation shows that the proposed denoising method achieves better results, compared to the previous denoising methods using the indexes of SNR and RMSE. The experiment demonstrates that it is efficient for denoising VPVS polluted by the trend and random noise.
Copyright © 2017 Mingzhu Li et al. 2017
This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Wavelet threshold denoising process, where s ( n ) is the original noisy signal, t j , k is the wavelet coefficient obtained from the wavelet decomposition of s ( n ) , t j , k includes the approximate coefficient c j , k and the detail coefficient d i , k , v j , k is the estimated wavelet coefficient after wavelet threshold denoising, and f ( n ) is the estimated s ( n ) obtained from the wavelet reconstruction of v j , k .
Comparison with hard and soft thresholding functions.
Comparison with Zhang’s and Nasri’s thresholding functions.
Comparison with Wang’s thresholding function.
TNN structure of unsupervised learning, where t 1 , k , t 2 , k , … , t j , k are the wavelet coefficients obtained from the wavelet decomposition of signal s ( n ) , t i 1 , k , t i 2 , k , … , t i j , k are the normalized wavelet coefficients, v i 1 , k , v i 2 , k , … , v i j , k are the new normalized wavelet coefficients tuned by thresholding function (11), and the optimal thresholds of thresholding function (11) are selected by (12) and (13), and v 1 , k , v 2 , k , … , v j , k are the antinormalized wavelet coefficients, which is used for the wavelet reconstruction of signal f ( n ) .
The original sine VPVS model and sine VPVS model.
The original sweep VPVS model and sine VPVS model.
The power spectral distribution of trend.
The energy distribution of VPVS model.
Flow chart of proposed VPVS denoising method.
The denoising results of sine VPVS model.
The denoising results of sweep VPVS model.
The apparatus of vehicle platform vibration test.
The power spectral analysis of VPVS.
The denoised results of VPVS.
Zhiqian Wang.Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, Jilin, China, firstname.lastname@example.org
Mingzhu Li,Zhiqian Wang,Jun Luo,Yusheng Liu,Sheng Cai. Wavelet Denoising of Vehicle Platform Vibration Signal Based on Threshold Neural Network. Shock and Vibration ,Vol.2017(2017)
|||M. Nasri, H. Nezamabadi-pour. (2009). Image denoising in the wavelet domain using a new adaptive thresholding function. Neurocomputing.72(4–6):1012-1025. DOI: 10.1109/18.382009.|
|||Z. Xia, X. Wang, X. Sun, Q. Liu. et al.(2016). Steganalysis of LSB matching using differences between nonadjacent pixels. Multimedia Tools and Applications.75(4):1947-1962. DOI: 10.1109/18.382009.|
|||X. Wang, X. Ou, B.-W. Chen, M. Kim. et al.(2015). Image denoising based on improved wavelet threshold function for wireless camera networks and transmissions. International Journal of Distributed Sensor Networks.2015-23. DOI: 10.1109/18.382009.|
|||B. Gu, V. S. Sheng, K. Y. Tay, W. Romano. et al.(2015). Incremental support vector learning for ordinal regression. IEEE Transactions on Neural Networks and Learning Systems.26(7):1403-1416. DOI: 10.1109/18.382009.|
|||B. Gu, V. S. Sheng. (2016). A robust regularization path algorithm for -support vector classification. IEEE Transactions on Neural Networks and Learning Systems:1-8. DOI: 10.1109/18.382009.|
|||Z. Pan, Y. Zhang, S. Kwong. (2015). Efficient motion and disparity estimation optimization for low complexity multiview video coding. IEEE Transactions on Broadcasting.61(2):166-176. DOI: 10.1109/18.382009.|
|||C. L. Zhang. (2003). Study on Active Vibration Control of Micro-Manufacturing Platform. DOI: 10.1109/18.382009.|
|||X. Hu, J. Wang. (2006). The Application of MATLAB in Signal Processing. DOI: 10.1109/18.382009.|
|||C. M. Stein. (1981). Estimation of the mean of a multivariate normal distribution. The Annals of Statistics.9(6):1135-1151. DOI: 10.1109/18.382009.|
|||X. Wen, L. Shao, Y. Xue, W. Fang. et al.(2015). A rapid learning algorithm for vehicle classification. Information Sciences.295(1):395-406. DOI: 10.1109/18.382009.|
|||T.-W. Yang, P.-F. Chen, J.-D. Han, W.-L. Xu. et al.(2015). Wavelet transform analysis of optic fiber force sensing signals at puncture needle tip. Optics and Precision Engineering.23(8):2149-2157. DOI: 10.1109/18.382009.|
|||Y.-P. Zang, D.-J. Zhang, W.-Z. Wang. (2009). Per-level threshold de-noising method using wavelet and its application in engine vibration analysis. Journal of Vibration and Shock.28(8):57-60. DOI: 10.1109/18.382009.|
|||W. Deng, R. Chen, B. He, Y. Q. Liu. et al.(2012). A novel two-stage hybrid swarm intelligence optimization algorithm and application. Soft Computing.16(10):1707-1722. DOI: 10.1109/18.382009.|
|||R. Yan, R. X. Gao, X. Chen. (2014). Wavelets for fault diagnosis of rotary machines: a review with applications. Signal Processing.96:1-15. DOI: 10.1109/18.382009.|
|||W. Deng, H. Zhao, J. Liu, X. Yan. et al.(2014). An improved CACO algorithm based on adaptive method and multi-variant strategies. Soft Computing.19(3):701-713. DOI: 10.1109/18.382009.|
|||J. Li, T. Jiang, S. Grzybowski, C. Cheng. et al.(2010). Scale dependent wavelet selection for de-noising of partial discharge detection. IEEE Transactions on Dielectrics and Electrical Insulation.17(6):1705-1714. DOI: 10.1109/18.382009.|
|||D. L. Donoho, I. M. Johnstone. (1995). Adapting to unknown smoothness via wavelet shrinkage. Journal of the American Statistical Association.90(432):1200-1224. DOI: 10.1109/18.382009.|
|||J. Li, C. Cheng, T. Jiang, S. Grzybowski. et al.(2012). Wavelet de-noising of partial discharge signals based on genetic adaptive threshold estimation. IEEE Transactions on Dielectrics and Electrical Insulation.19(2):543-549. DOI: 10.1109/18.382009.|
|||B. Gu, X. Sun, V. S. Sheng. (2016). Structural minimax probability machine. IEEE Transactions on Neural Networks and Learning Systems. DOI: 10.1109/18.382009.|
|||W.-Y. Dong, H. Ding, X.-S. Dong, Y.-F. Wang. et al.(2015). An adaptive wavelet threshold de-nosing both in low and high frequency domains. Acta Electronica Sinica.43(12):2374-2380. DOI: 10.1109/18.382009.|
|||X.-P. Zhang. (2001). Thresholding neural network for adaptive noise reduction. IEEE Transactions on Neural Networks.12(3):567-584. DOI: 10.1109/18.382009.|
|||R. Yang, M. Ren. (2011). Wavelet denoising using principal component analysis. Expert Systems with Applications.38(1):1073-1076. DOI: 10.1109/18.382009.|
|||Y. Zheng, B. Jeon, D. Xu, Q. M. J. Wu. et al.(2015). Image segmentation by generalized hierarchical fuzzy C-means algorithm. Journal of Intelligent and Fuzzy Systems.28(2):961-973. DOI: 10.1109/18.382009.|
|||L. Jing-Yi, L. Hong, Y. Dong, Z. Yan-Sheng. et al.(2016). A new wavelet threshold function and denoising application. Mathematical Problems in Engineering.2016-8. DOI: 10.1109/18.382009.|
|||D. L. Donoho. (1995). De-noising by soft-thresholding. Institute of Electrical and Electronics Engineers. Transactions on Information Theory.41(3):613-627. DOI: 10.1109/18.382009.|