噪声与振动控制2025，Vol.45Issue(2)：76-81,6.DOI:10.3969/j.issn.1006-1355.2025.02.013
变转速下基于改进ConvLSTM的滚动轴承故障诊断
Fault Diagnosis of Rolling Bearings Based on Improved Convolutional LSTM Networks under Variable Speed Conditions
摘要
Abstract
Aiming at the problem of fault features being overwhelmed under variable speed operating conditions with different noise levels from multiple sensors,a fault diagnosis method based on an improved Convolutional Long Short-Term Memory network(ConvLSTM)was proposed.Firstly,the one-dimensional vibration signals collected from multiple sensors were decomposed into two-dimensional matrix sequences.Then,an improved ConvLSTM unit consisting of the feature ex-traction layer was utilized to extract both temporal and spatial features within the signals,where the improvement means to replace the regular convolution in a traditional ConvLSTM input gate with dilated convolution,so that it has a larger recep-tive field to read input information under the same convolution kernel.Finally,the classification output layer was constructed with convolutional layer and Global Average Pooling(GAP)and the diagnosis results were obtained.The method was vali-dated by using the CWRU rolling bearing dataset and XJTU-SY rolling bearing dataset.Experiment demonstrates that com-pared to other benchmark models,the improved ConvLSTM model can attain higher accuracy under variable speeds with dif-ferent noise levels and is less affected by sample size.关键词
故障诊断/滚动轴承/变转速工况/深度学习/ConvLSTMKey words
fault diagnosis/rolling bearings/variable speed/deep learning/convolutional LSTM分类
机械制造引用本文复制引用
黄金鹏,吴国新,刘秀丽..变转速下基于改进ConvLSTM的滚动轴承故障诊断[J].噪声与振动控制,2025,45(2):76-81,6.基金项目
国家重点研发计划资助项目(2020YFB1713203) （2020YFB1713203）
北京信息科技大学勤信人才资助项目(QXTCPC202120) （QXTCPC202120）
机电系统测控北京市重点实验室开放课题资助项目(KF20222223201) （KF20222223201）
