基于DBNs的车辆悬架减振器异响鉴别方法

黄海波; 李人宪; 杨琪; 丁渭平; 杨明亮

doi:10.3969/j.issn.0258-2724.2015.05.002

基于DBNs的车辆悬架减振器异响鉴别方法

doi: 10.3969/j.issn.0258-2724.2015.05.002

基金项目:

中央高校基本科研业务费专项资金资助项目(SWJTU12CX036)

详细信息

作者简介:
黄海波(1989-),男,博士研究生,研究方向为车辆声振舒适性、车辆系统动力学,E-mail:451126547@qq.com

通讯作者:
丁渭平(1968-),男,教授,博士,研究方向为车辆声振舒适性、车辆系统动力学,E-mail:dwpc@263.net

计量
- 文章访问数: 853
- HTML全文浏览量: 86
- PDF下载量: 470
- 被引次数: 0
出版历程
- 收稿日期: 2014-09-02
- 刊出日期: 2015-10-25

Identifying Abnormal Noise of Vehicle Suspension Shock Absorber Based on Deep Belief Networks

摘要

摘要: 针对人工经验提取特征进行减振器异响鉴别的复杂性与不可扩展性的问题,分析了深度信念网络(deep belief networks,DBNs)在减振器异响鉴别中的应用,并结合减振器整车与台架试验提出了完整的减振器异响鉴别流程.该方法只需将收集到的减振器活塞杆顶端振动加速度信号作为输入,经过DBNs模型逐层特征学习便可进行减振器异响鉴别.同时将鉴别结果与经典的BP神经网络、支持向量机以及传统的3种人工特征提取方法进行对比分析.结果表明:在输入仅为原始信号的条件下,深度信念网络模型对减振器异响鉴别的准确率为96.7%,表明了深度信念网络在减振器异响甄别中的优越性,具有广泛的工程应用前景.
- 减振器 /
- 异响鉴别 /
- 深度学习 /
- 玻尔兹曼机 /
- 深度信念网络
Abstract: Considering the complexity and non-expandability of extracting abnormal noise features of shock absorbers by experience and manual work, applications of deep belief networks (DBNs) to identification of vehicle suspension shock absorber's abnormal noise are discussed, and a complete identification process of shock absorber abnormal noise is proposed by combining the shock absorber's road test with its rig test. The method only needs to take the vibration acceleration signal of the shock absorber piston rod as input, and then process the signal by learning layer-wise features in the DBNs model to classify the sounds of shock absorbers. In addition, the identification accuracy by DBNs is compared with that by the classical BP neural network, support vector machine, and other three traditional abnormal noise identification methods. The results show that when only the original signal is used as input, the classification accuracy by DBNs is 96.7%, which is higher than that by the other five methods. This illustrates the superiority of the DBNs algorithm in identifying the abnormal noise of shock absorbers and may imply a wide prospect in engineering application.
- shock absorber /
- abnormal noise identification /
- deep learning /
- restricted Boltzmann machine /
- deep belief networks

HTML全文

参考文献(43)

舒红宇,王立勇,吴碧华,等. 液力减振器结构异响发生的微过程分析

[J]. 振动工程学报,2005,18(3): 282-287. SHU Hongyu, WANG Liyong, WU Bihua, et al. Analysis on the abnormal structure noise yielding processofhydraulic shock absorber

BENAZIZ M, NACIVET S, DEAK J, et al. Double tube shock absorber model for noise and vibration analysis

[J]. Journal of Vibration Engineering, 2005, 18(3): 282-287.

宋睿. 汽车双筒式减振器异响的产生机理与控制方法研究

么鸣涛,顾亮,管继富. 双筒式减振器异响试验分析

[J]. SAE International Journal of Passenger Cars Mechanical Systems, 2013, 6(2): 1177-1185.

丁渭平. 汽车底盘系统NVH及异响控制技术研究

黄海波,李人宪,丁渭平,等. 基于台架试验的悬架减振器异响辨识研究

余凯,贾磊,陈雨强,等. 深度学习的昨天、今天和明天

[D]. 成都:西南交通大学,2012.

张建平,胡明华,吴振亚,等. 基于BP网络的空中交通管制运行品质评价

[J]. 工程设计学报,2010,17(3): 229-235. YAO Mingtao, GU Liang, GUAN Jifu. Test analysis on the noise of automobile shock absorber

吴志周,范宇杰,马万经. 基于灰色神经网络的点速度预测模型

[J]. Journal of Engineering Design, 2010, 17(3): 229-235.

YOON J, YANG I, JEONG J, et al. Reliability improvement of a sound quality index for a vehicle HVAC systemusing a regression and neural network model

秦娜,金炜东,黄进,等. 基于EEMD样本熵的高速列车转向架故障特征提取

HINTON G E, SALAKHUTDINOV R. Reducing the dimensionality of data with neural network

[C]//汽车NVH控制技术国际研讨会. 成都:

BENGIO Y. Learning deep architectures for AI

[s.n.],2013: 93-106.

AREL I, ROSE D C, KARNOWSKI T P. Deep machine learning: a new frontier in artificial intelligence research

[J]. 振动与冲击,2015,34(2): 191-196. HUANG Haibo, LI Renxian, DING Weiping, et al. Rig test for identifying abnormal noise of suspension shock absorber

HINTON G E. Training products of experts by minimizing contrastive divergence

GRAVES A, MOHAMED A R, HINTON G E. Speech recognition with deep recurrent neura inetworks

[J]. Journal of Vibration and Shock, 2015, 34(2): 191-196.

HINTON G E. Training products of experts by minimizing contrastive divergence

[J]. 计算机研究与发展,2013,50(9): 1799-1804. YU Kai, JIA Lei, CHEN Yuqiang, et al. Deep learning: yesterday, today, and tomorrow

[J]. Journal of Computer Research and Development, 2013, 50(9): 1799-1804.

[J]. 西南交通大学学报,2013,48(3): 553-558. ZHANG Jianping, HU Minghua, WU Zhenya, et al. An improved integrated evaluation method on operation performance of air traffic control based on BP network

[J]. Journal of Southwest Jiaotong University, 2013, 48(3): 553-558.

[J]. 西南交通大学学报,2012,47(2): 285-290. WU Zhizhou, FAN Yujue, MA Wanjing. Spot speed prediction model based on grey neural network

[J]. Journal of Southwest Jiaotong University, 2012, 47(2): 285-290.

[J]. Applied Acoustics, 2012, 73: 1099-1103.

[J]. 西南交通大学学报,2014,49(1): 27-32. QIN Na, JIN Weidong, HUANG Jin, et al. Feature extraction of high speed train bogie based on ensemble empirical mode decomposition and sample entropy

[J]. Journal of Southwest Jiaotong University, 2014, 49(1): 27-32.

[J]. Science, 2006, 313: 504-507.

[J]. Foundations and Trends in Machine Learning, 2009, 2(1): 1-127.

[J]. IEEE Computational Intelligence Magazine, 2010, 5(4): 13-18.

[J]. Neural Computation, 2002, 14(8): 1771-1880.

[C]//Acoustics, Speech and Signal Processing (ICASSP), IEEE International Conference. Santa Clara:

[s. n.]2013: 6645-6649.

[J]. Neural Computation, 2002, 14(8): 1771-1880.

施引文献

附加材料(0)

访问统计