摘要
机械设备实际运行中的工况具有时变性,这加剧了源域(训练集)和目标域(测试集)数据之间的分布差异,因而导致智能故障诊断模型的性能下降。提出了一种基于深度对比迁移学习的方法,可用于机械设备变工况下的故障智能诊断。利用多层卷积块作为模型前置特征提取器,能够有效提取原始振动数据的代表性特征,提升故障分类器和域判别器的诊断性能。将前置特征提取器提取的特征传递给特征融合器,特征融合器提炼并联接局部感受野和全局感受野卷积特征,增强模型特征表达能力。将特征融合器提炼的特征用于故障分类器和域判别器诊断不同工况下的机械故障,并在故障分类器中使用Wasserstein距离度量源域和目标域数据的差异,基于互信息噪声对比估计提出用于工况区分的互信息对比域判别器,提高模型的迁移诊断性能。将所提方法用于诊断变工况下不同类别的轴承、齿轮故障。结果表明,所提方法能够有效实现变工况下轴承、齿轮故障的迁移诊断。
The distribution discrepancy between source domain data and target domain data will be aggravated due to time-changing operation conditions of the mechanical equipment in practical.Therefore,the performance of the intelligent fault diagnosis model is weakened.A novel method based on deep contrastive transfer learning is proposed for mechanical fault diagnosis under variable working conditions.Multilayer convolution block is used as the prepositive feature extractor to extract representative features from raw vibration data,which can improve the performance of fault classifier and domain discriminator.The feature extracted from prepositive feature extractor is transmitted to feature fusion device,and the convolution features can be refined and connected by the local and global receptive fields in prepositive feature extractor which can strengthen the feature-expressed capacity of the model.The refined features are utilized for fault classifier and domain discriminator to diagnose mechanical fault under different conditions.The Wasserstein distance is applied in fault classifier for measuring the discrepancy between source and target domain data.Based on the mutual information noise contrastive estimation,the mutual information domain discriminator is proposed to distinguish working conditions.All of them can raise the transfer capacity of the proposed method.Experiments on bearing and gear dem‑onstrate that the proposed method diagnoses mechanical faults under variable working conditions based on transfer tasks effectively.
作者
苏浩
杨鑫
向玲
胡爱军
李显泽
SU Hao;YANG Xin;XIANG Ling;HU Ai-jun;LI Xian-ze(Mechanical Engineering Department,North China Electric Power University,Baoding 071003,China;Hebei Key Laboratory of Electric Machinery Health Maintenance&Failure Prevention,Baoding 071003,China)
出处
《振动工程学报》
EI
CSCD
北大核心
2023年第3期845-853,共9页
Journal of Vibration Engineering
基金
国家自然科学基金资助项目(52075170,52175092)。
关键词
故障诊断
变工况
Wasserstein距离
迁移学习
对比学习
fault diagnosis
variable working conditions
Wasserstein distance
transfer learning
contrastive learning
