• CN:11-2187/TH
  • ISSN:0577-6686

机械工程学报 ›› 2019, Vol. 55 ›› Issue (7): 81-88.doi: 10.3901/JME.2019.07.081

• 基于深度学习的机械装备故障预测与健康管理 • 上一篇    下一篇

独立自适应学习率优化深度信念网络在轴承故障诊断中的应用研究

沈长青, 汤盛浩, 江星星, 石娟娟, 王俊, 朱忠奎   

  1. 苏州大学轨道交通学院 苏州 215131
  • 收稿日期:2018-06-11 修回日期:2018-11-09 出版日期:2019-04-05 发布日期:2019-04-05
  • 通讯作者: 朱忠奎(通信作者),男,1974年出生,博士,教授,博士研究生导师。主要研究方向为车辆系统动力学与控制、机械故障诊断。E-mail:zhuzhongkui@suda.edu.cn
  • 作者简介:沈长青,男,1987年出生,博士,副教授,硕士研究生导师。主要研究方向为机械状态信号处理、监测与智能诊断。E-mail:cqshen@suda.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(51875375,51875376)。

Bearings Fault Diagnosis Based on Improved Deep Belief Network by Self-individual Adaptive Learning Rate

SHEN Changqing, TANG Shenghao, JIANG Xingxing, SHI Juanjuan, WANG Jun, ZHU Zhongkui   

  1. School of Rail Transportation, Soochow University, Suzhou 215131
  • Received:2018-06-11 Revised:2018-11-09 Online:2019-04-05 Published:2019-04-05

摘要: 对机械装备轴承等关键对象的健康状态监测正在步入大数据、智能化时代。传统的轴承故障诊断方法大多数依靠人工提取特征,这需要依赖于复杂的信号处理方法以及丰富的专业经验积累。深度学习方法作为一种可以学习数据深层次特征的新的机器学习方法,将其引入机械故障诊断领域,并对其运行效率、故障识别精度进行提升,将进一步提高基于深度学习方法在故障诊断领域的实用性。提出一种基于Nesterov动量法的独立自适应学习率优化的深度信念网络,引入Nesterov动量法代替传统动量法预测参数下降的位置,控制参数达到最优点的速度,避免了传统动量法引起的错过最优点问题;利用独立自适应学习率在梯度更新时自适应选择下降步长,加快模型训练,提高模型的泛化能力。试验结果表明,在诊断精度上,相比支持向量机和标准深度信念网络,提出的方法对不同载荷工况下轴承故障识别均获得了最高的精度;在运行效率上,相比现有一些优化算法,该优化模型能够稳定有效的加快模型训练速度,提升深度信念网络的泛化能力,有效地实现轴承故障诊断。

关键词: Nesterov动量法, 独立自适应学习率, 故障诊断, 机械装备, 深度信念网络

Abstract: The health monitoring of key component of mechanical equipment such as bearings is entering the era of big data and intelligence. The traditional method of bearing fault diagnosis depends on manual extraction, which relies on complex signal processing methods and abundant professional experience. As a new machine learning method which can learn deep features from data, the deep learning method is introduced into the field of mechanical fault diagnosis, and the operation efficiency and fault recognition accuracy of mechanical fault diagnosis are improved, which will further improve the practicability of deep learning method in fault diagnosis field. A novel self-adaptive deep belief network with Nesterov momentum (NM-based ADDBN) is proposed. Nesterov momentum is used to replace the traditional momentum method to predict the next position of the parameters, and control parameters' speed towards the optimal values, avoiding missing the optimal values caused by the traditional momentum method. Self-individual adaptive learning rate is used to adaptively select decrease step length for the gradient update, and to speed up the model training and improve the generalization ability of the model. Experimental results show that compared with support vector machine and standard depth belief network, the proposed method obtain the best precision performance for bearing fault recognition under different load conditions. For operational efficiency, the optimization model can effectively and steadily speed up the model training, improve generalization ability of deep belief network, and realize the rolling bearing fault diagnosis effectively compared with current optimization methods.

Key words: deep belief network, fault diagnosis, mechanical equipment, Nesterov momentum, self-individual adaptive learning rate

中图分类号: