Li Xiaohu, Wan Shaoke, Liu Shijie, Zhang Yanfei, Hong Jun, Wang Dongfeng
Key Laboratory of Education Ministry for Modern Design & Rotor-Bearing System, Xi'an Jiaotong University, China; School of Mechanical Engineering, Xi'an Jiaotong University, China.
Key Laboratory of Education Ministry for Modern Design & Rotor-Bearing System, Xi'an Jiaotong University, China; School of Mechanical Engineering, Xi'an Jiaotong University, China.
ISA Trans. 2022 Sep;128(Pt B):550-564. doi: 10.1016/j.isatra.2021.11.020. Epub 2021 Dec 8.
The methods with multi-sensor data fusion have been a remarkable way to improve the accuracy and robustness of bearing fault diagnosis under complicated conditions. However, most of the existing fusion models or methods belong to single fusion level and simple fusion structure is usually utilized, and the correlation and complementarity of information between multi-sensor data might be easily ignored. In order to improve the performance of fault diagnosis with multi-sensor data fusion, this paper proposes a novel model of multi-layer deep fusion network with attention mechanism (AMMFN). The proposed model consists of a central network and multiple branch networks stacking by Inception networks, and the deep features of each single-sensor data are extracted automatically by the branch networks, and the extracted features of multi-sensor data at different levels are fused with the central network, and then the information interaction between multi-sensor data can be significantly enhanced and the adaptive hierarchical fusion of information can be achieved. Moreover, a fusion strategy based on attention mechanism is designed to extract more correlation information during the fusion of features extracted from multi-sensor data. Extensive experiments are also performed to evaluate the performance of proposed approach, and the comparison results with other methods indicate that the presented method takes higher accuracy and stronger generalization ability.
多传感器数据融合方法已成为在复杂条件下提高轴承故障诊断准确性和鲁棒性的一种显著方式。然而，现有的大多数融合模型或方法都属于单一融合级别，通常采用简单的融合结构，多传感器数据之间信息的相关性和互补性可能很容易被忽略。为了提高多传感器数据融合故障诊断的性能，本文提出了一种具有注意力机制的新型多层深度融合网络模型（AMMFN）。所提出的模型由一个中心网络和多个由Inception网络堆叠而成的分支网络组成，分支网络自动提取每个单传感器数据的深度特征，不同级别多传感器数据提取的特征与中心网络融合，从而可以显著增强多传感器数据之间的信息交互并实现信息的自适应分层融合。此外，设计了一种基于注意力机制的融合策略，以便在多传感器数据提取的特征融合过程中提取更多相关信息。还进行了大量实验来评估所提方法的性能，与其他方法的比较结果表明，所提出的方法具有更高的准确性和更强的泛化能力。
