A Calculation Method of Auditory Saliency Map for Representation of Transient Vibration Signal

doi:10.3901/JME.2018.07.054

Abstract

Abstract: The transient vibration signal always is a significant symbol of mechanical fault, and can lead to a prominent change on amplitude and frequency structure of signal. A method named auditory saliency map is introduced to vibration signal analysis, and according to the shape characteristic in time-frequency domain of transient signal, a novel calculation method of auditory saliency map is proposed based on the operating mechanism of auditory system. The signal is band-pass filtered by Gammatone filters firstly, and the envelope filter signal is extracted and compressed nonlinearly. Then the multi-scale two-dimension and one-dimension low-pass filter is carried out respectively. To highlight the time-frequency regions, in which the signal change observably, the filter results are integrated between different filter scale. At last, by synthesizing integrate results in two kinds of filter, the time-frequency saliency and global saliency are received. The results of numerical simulation and experimental verification show that the proposed method can effectively represent the time-frequency regions of transient signal, moreover, compared with existing methods, in the aspects of anti-noise, masking stationary background signal and representing weak transient signal, the propose method has better performance.

Key words: auditory model, band-pass filter, faults diagnosis, low-pass filter, transient signal

CLC Number:

TH17

LI Yungong, DAI Li, LI Guomeng, WANG Bo, WU Wenshou. A Calculation Method of Auditory Saliency Map for Representation of Transient Vibration Signal[J]. Journal of Mechanical Engineering, 2018, 54(7): 54-62.

References

[1] 张欣,夏秀渝,王雪君. 一种听觉显著图提取模型[J]. 四川大学学报, 2014, 51(2):292-298. ZHANG Xin, XIA Xiuyu, WANG Xuejun. A saliency map extraction model for auditory attention[J]. Journal of Sichuan University, 2014, 51(2):292-298.
[2] WANG J Y, ZHANG K, MADANI K, et al. Salient environmental sound detection framework for machine awareness[J]. Neurocomputing, 2015, 152:444-454.
[3] KAYA E M, ELHILALI M. A temporal saliency map for modeling auditory attention[C]//201246th Annual Conference on Information Sciences and Systems (CISS), March21-23, 2012, Princeton University, Princeton.New York:IEEE, 2012:1-6.
[4] 朱莉,郑奋,邓娟,等. 听觉选择性注意的可塑性及其神经机制研究[J]. 生物化学与生物物理进展, 2015, 42(7):647-661. ZHU Li, ZHENG Fen, DENG Juan, et al. Research on neural mechanisms of plasticity in auditory selective attention[J]. Progress in Biochemistry and Biophysics, 2015, 42(7):647-661.
[5] 刘冬云,赵岩,肖中举. 短声改变听觉中枢下丘神经元对纯音的反应特性[J]. 华南国防医学杂志,2013,27(8):536-539. LIU Dongyun,ZHAO Yan,XIAO Zhongju. Click changes the response property of inferior colliculers neurons to tone of mouse[J]. Military Medical Journal of South China, 2013, 27(8):536-539.
[6] 张龙,熊国良,黄文艺. 复小波共振解调频带优化方法和新指标[J]. 机械工程学报, 2015, 51(3):129-138. ZHANG Long, XIONG Guoliang, HUANG Wenyi. New procedure and index for the parameter optimization of complex wavelet based resonance demodulation[J]. Journal of Mechanical Engineering, 2015, 51(3):129-138.
[7] 吴小涛,杨锰,袁晓辉,等. 基于峭度准则EEMD及改进形态滤波方法的轴承故障诊断[J].振动与冲击, 2015, 34(2):38-44. WU Xiaotao, YANG Meng, YUAN Xiaohui, et al. Bearing fault diagnosis using EEMD and improved morphological filtering method based on kurtosis criterion[J]. Journal of Vibration and Shock, 2015, 34(2):38-44.
[8] 张丹, 隋文涛. 基于子小波布置和系数融合的轴承故障诊断[J]. 振动、测试与诊断, 2016, 36(1):182-186. ZHANG Dan, SUI Wentao. Research on the characteristics of flow-induced vibration of bulkhead gate based on chaotic theory[J]. Journal of Vibration, Measurement & Diagnosis, 2016, 36(1):182-186.
[9] JENA D P, SAHOO S, PANIGRAHI S N. Gear fault diagnosis using active noise cancellation and adaptive wavelet transform[J]. Measurement, 2014, 47:356-372.
[10] BERT D C, DICK B. A model of saliency-based auditory attention to environmental sound[C]//Proceedings of 20th International Congress on Acoustics, August 23-27, 2010, Sydney, Australia. New York:Curran Associates, 2010:1-8.
[11] LAURENCE M, SYLVAIN C.Saliency model of auditory attention based on frequency, amplitude and spatial location[C]//2015 International Joint Conference on Neural Networks (IJCNN), July 11-27, 2015, Killarney Ireland. New York:IEEE, 2015:1-5.
[12] RUŽICA B, ZORAN Š, SLOBODAN T J, et al. Automatic detection of stridence in speech using the auditory model[J]. Computer Speech and Language, 2016, 36:122-135.
[13] CHEN X Y, SONG M L, XUE L X, et al.An audio-visual human attention analysis approach to abrupt change detection in videos[J]. Signal Processng, 2015, 110:143-154.
[14] GAO B, WOO W L, DLAY S S. Unsupervised singlechannel separation of nonstationary signals using gammatone filterbank and itakura-saito nonnegative matrix two-dimensional factorizations[J]. IEEE Transactions on Circuits and Systems, 2013, 60(3):662-675.
[15] LI Y G, ZHANG J P, DAI L, et al. Auditory-model-based feature extraction method for mechanical faults diagnosis[J]. Chinese Journal of Mechanical Engineering, 2010, 21(3):391-397.