基于深度置信网络与信息融合的齿轮故障诊断方法

PDF(1680 KB)

振动与冲击 ›› 2021, Vol. 40 ›› Issue (8) : 62-69.

论文

李益兵1,2，黄定洪1，马建波1，江丽1,2

作者信息 +

A gear fault diagnosis method based on deep belief network and information fusion

LI Yibing1,2，HUANG Dinghong1，MA Jianbo1，JIANG Li1,2

Author information +

文章历史 +

摘要

针对齿轮在复杂运行工况下故障特征提取困难，传统故障诊断方法的识别精度易受人工提取特征的影响，以及单传感器获取信息不全面等问题，提出基于深度置信网络(DBN)与信息融合的齿轮故障诊断方法。通过多传感器信息融合技术对每个传感器采集的振动信号进行数据层融合；利用DBN进行自适应特征提取从而实现故障分类。为了避免因人为选择DBN结构参数，导致模型识别精度下降的问题，利用改进的混合蛙跳算法(ISFLA)对DBN结构参数进行优化。试验表明，与BP神经网络、未经优化的DBN以及单传感器故障诊断相比，该研究提出的信息融合及优化方法具有更高的故障识别精度。

Abstract

It is difficult to extract the fault features of gears under complex operation conditions. The traditional fault diagnosis and recognition accuracy are easily affected by the manual feature extraction, and the information obtained by a single sensor is not comprehensive. To solve the above problems, a gear fault diagnosis method based on deep belief networks (DBN) and information fusion was proposed in this paper. Firstly, the vibration signals collected by each sensor were fused by multi-sensor information fusion technology at the data layer, and then DBN was used for adaptive feature extraction to achieve fault classification. In order to avoid the problem of model recognition accuracy degradation caused by artificial selection of DBN structural parameters, an improved shuffled frog leaping algorithm (ISFLA) was proposed to optimize DBN structural parameters. Experiments show that the information fusion and optimization methods proposed in this paper have higher fault recognition accuracy than BP neural network, DBN, and single sensor fault diagnosis.

导出引用

李益兵1,2，黄定洪1，马建波1，江丽1,2. 基于深度置信网络与信息融合的齿轮故障诊断方法[J]. 振动与冲击, 2021, 40(8): 62-69

LI Yibing1,2，HUANG Dinghong1，MA Jianbo1，JIANG Li1,2. A gear fault diagnosis method based on deep belief network and information fusion[J]. Journal of Vibration and Shock, 2021, 40(8): 62-69

参考文献

［1］魏莎,韩勤锴,褚福磊.考虑不确定性因素的齿轮系统动力学研究综述［J］.机械工程学报, 2016,52(1): 1-19.
WEI Sha, HAN Qinkai, CHU Fulei. Review on research of uncertain dynamics for gear system［J］. Journal of Mechanical Engineering, 2016,52(1): 1-19.

［2］胡茑庆,陈徽鹏,程哲,等.基于经验模态分解和深度卷积神经网络的行星齿轮箱故障诊断方法［J］.机械工程学报, 2019,55(7): 9-18.
HU Niaoqing, CHEN Huipeng, CHENG Zhe, et al. Fault diagnosis for planetary gearbox based on EMD and deep convolutional neural networks［J］. Journal of Mechanical Engineering, 2019,55(7): 9-18.

［3］辛玉,李舜酩,王金瑞,等.基于迭代经验小波变换的齿轮故障诊断方法［J］.仪器仪表学报, 2018,39(11): 79-86.
XIN Yu, LI Shunming, WANG Jinrui, et al.Gear fault diagnosis method based on iterative empirical wavelet transform［J］. Chinese Journal of Scientific Instrument, 2018,39(11): 79-86.

［4］HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets［J］. Neural Computation, 2006,18(7): 1527-1554.

［5］YAN J H, HU Y Y, GUO C Z. Rotor unbalance fault diagnosis using DBN based on multi-source heterogeneous information fusion［J］. Procedia Manufacturing, 2019,35: 1184-1189.

［6］XU F, FANG Y J, WANG D, et al. Combining DBN and FCM for fault diagnosis of roller element bearings without using data labels［J］. Shock and Vibration, 2018,2018: 1-12.

［7］ZHANG T F, LI Z, DENG Z H, et al. Hybrid data fusion DBN for intelligent fault diagnosis of vehicle reducers［J］. Sensors, 2019,19(11): 1-23.

［8］陈保家,刘浩涛,徐超,等.深度置信网络在齿轮故障诊断中的应用［J］.中国机械工程, 2019,30(2): 205-211.
CHEN Baojia, LIU Haotao, XU Chao, et al. Gear fault diagnosis on DBNS［J］. China Mechanical Engineering, 2019,30(2): 205-211.

［9］郑小霞,陈广宁,任浩翰,等.基于改进VMD和深度置信网络的风机易损部件故障预警［J］.振动与冲击, 2019,38(8): 153-160.
ZHENG Xiaoxia, CHEN Guangning, REN Haohan, et al. Fault detection of vulnerable units of wind turbine based on improved VMD and DBN［J］. Journal of Vibration and Shock, 2019,38(8): 153-160.

［10］SHAO H, JIANG H, ZHANG X, et al. Rolling bearing fault diagnosis using an optimization deep belief network［J］. Measurement Science and Technology, 2015,26(11): 1-17.

［11］李松柏,康子剑,陶洁.基于信息融合及堆栈降噪自编码的齿轮故障诊断［J］.振动与冲击, 2019,38(5): 216-221.
LI Songbai, KANG Zijian, TAO Jie. Gear fault diagnosis based on information fusion and stacked de-noising auto-encoder［J］. Journal of Vibration and Shock, 2019,38(5): 216-221.

［12］EUSUFF M, LANSEY K, PASHA F. Shuffled frog-leaping algorithm: a memetic meta-heuristic for discrete optimization［J］. Engineering Optimization, 2006,38(2): 129-154.

［13］HINTON G E. A practical guide to training restricted Boltzmann machines［M］//Neural Networks: Tricks of the Trade. Berlin: Springer, 2012.

［14］HINTON G E. Training products of experts by minimizing contrastive divergence［J］. Neural Computation, 2002,14(8): 1771-1800.

［15］ZHANG X, HU X, CUI G, et al. An improved shuffled frog leaping algorithm with cognitive behavior［C］//7th World Congress on Intelligent Control and Automation. ［S.l.］: IEEE, 2008.

［16］马平莉.混合蛙跳算法研究［D］. 西安：西安电子科技大学, 2013.

［17］LIU J, HU Y, WANG Y, et al. An integrated multi-sensor fusion-based deep feature learning approach for rotating machinery diagnosis［J］. Measurement Science and Technology, 2018,29(5): 1-12.

［18］KINGMA D P, BA J. Adam: a method for stochastic optimization［C］// 3rd International Conference on Learning Representations. San Diego: ICLR, 2014.

［19］赵光权,葛强强,刘小勇.基于DBN的故障特征提取及诊断方法研究［J］.仪器仪表学报, 2016,37(9): 1947-1953.
ZHAO Guangquan, GE Qiangqiang, LIU Xiaoyong, et al. Fault feature extraction and diagnosis method based on deep belief network［J］. Chinese Journal of Scientific Instrument, 2016,37(9): 1947-1953.