摘要
针对滚动轴承在噪声环境中干扰大、工况复杂多变时诊断困难的问题,提出了一种改进深度残差网络的轴承故障诊断方法。对滚动轴承振动信号预处理,得到数据样本,分为训练集和测试集;将基于注意力机制的挤压与激励网络(squeeze-and-excitation networks,SENet)结构引入到残差神经网络残差块之中建立特征提取通道之间的联系,得到改进深度残差网络模型;再将标签化的训练集数据样本输入改进的诊断模型中进行训练;将训练好的诊断模型应用于测试集,输出每种故障的识别结果。在训练过程中,为了抑制过拟合,对原始训练样本进行加噪处理;同时引入了激活函数LReLU和Dropout技巧来提高模型的抗干扰能力。为了验证该模型的诊断性能,选用实验数据进行验证,结果表明该方法在载荷变化以及信号受到严重噪声污染时,依然拥有良好的故障诊断能力。
A new fault diagnosis method based on an improved depth residual network was proposed to solve the problems of rolling bearings in noisy environment with large interference and complex and changeable working conditions.Firstly,the vibration signal of rolling bearing was preprocessed to obtain data samples,which were divided into training set and test set.The attention-mechanism-based Squeeze and Excitation Network(SENet)structure was introduced into the residual neural network residual block to establish the connection between the feature extraction channels.The improved deep residual network model was located there.The labeled training set data were input into the improved diagnostic model for training.Finally,the trained diagnosis model was applied to the test set to output the identification results of each fault.In order to suppress overfitting,the original training samples were denoised.Meanwhile,the activation function LReLU and Dropout technique were introduced to improve the anti-interference ability of the model.In order to verify the diagnostic performance of the model,experimental data were selected for verification.The results show that the method has good fault diagnosis capability when the load changes and the signal is seriously polluted by noise.
作者
田科位
董绍江
姜保军
裴雪武
汤宝平
胡小林
赵兴新
TIAN Kewei;DONG Shaojiang;JIANG Baojun;PEI Xuewu;TANG Baoping;HU Xiaolin;ZHAO Xingxin(School of Mechantronics and Vehicle Engineering,Chongqing Jiaotong University,Chongqing,400074,China;The State Key Laboratory of Mechanical Transmission,Chongqing University,Chongqing 400030,China;Chongqing Innovation Center of Industrial Big-Data Co.Ltd,Chongqing 400056,China;Chongqing Changjiang Bearing Co.Ltd,Chongqing 401336,China)
出处
《振动与冲击》
EI
CSCD
北大核心
2021年第20期247-254,共8页
Journal of Vibration and Shock
基金
国家自然科学基金(51775072)。
关键词
滚动轴承
轴承故障诊断
深度残差网络
挤压与激励网络
rolling bearing
bearing fault diagnosis
deep residual network
extrusion and excitation network
