多小波系数增强动态聚合联邦深度网络的多工况故障诊断

针对分布式场景下单节点样本有限、多节点间工况分布不平衡等导致的深度学习故障诊断精度低的问题，提出一种多小波系数增强动态聚合联邦深度网络用于分布式小样本下的多工况机械故障诊断。提出多小波系数增强动态聚合联邦深度网络的诊断框架，单终端节点从本地样本中提取小波系数特征，提出多小波系数深度网络融合的特征增强方法，局部模型从多样性小波系数集合中提取更具判别性故障特征；聚合节点通过对多终端节点局部模型的聚合以构建全局联邦深度网络模型，并用于多工况故障诊断；为降低多节点间数据非独立同分布的影响，提出平衡模型贡献度的联邦动态加权聚合算法。轴承振动数据分析结果表明，所提方法能在分布式小样本条件下实现高精度的多工况故障诊断。

Multi-wavelet coefficients enhanced dynamic aggregation federal deep network for fault diagnosis under multiple conditions

To address the low accuracy of deep learning based fault diagnosis under distributed scenarios that caused by limited sample ofsingle node and unbalanced distribution of working conditions of multiple nodes, et al, a multi-wavelet coefficients enhanced dynamicaggregation federal deep network ( MWCE-FedDWA) is proposed for fault diagnosis under multiple conditions with distributed smallsamples. A framework for fault diagnosis using MWCE-FedDWA is proposed, wavelet coefficient features are extracted by each terminalnode from its local samples, a method based on multi-wavelet coefficient fusion in deep network is proposed for feature enhancement,each local model utilizes a set of diversified wavelet coefficients to extract more discriminative fault features. A global federal deepnetwork model is constructed in aggregation node by aggregating the local models from multiple terminal nodes, and then adopted for faultdiagnosis under multiple conditions. To reduce the influence of non-independent and identically distributed data among multiple nodes, afederated dynamic weighted aggregation algorithm is proposed to balance the contribution of local models. The results on bearing vibrationdata show that the proposed method can achieve high-precision diagnosis under multiple conditions with distributed small samples.