Adaptive Feature Utilization With Separate Gating Mechanism and Global Temporal Convolutional Network for Remaining Useful Life Prediction
Adaptive Feature Utilization With Separate Gating Mechanism and Global Temporal Convolutional Network for Remaining Useful Life Prediction
复制标题
DOI：
10.1109/jsen.2023.3299432
复制
发表时间：
2023-09
影响因子：
4.3
通讯作者：
Pengcheng Xia;Yixiang Huang;Chengjin Qin;Dengyu Xiao;Liang Gong;Chengliang Liu;Wenliao Du
中科院分区：
文献类型：
--
作者：
Pengcheng Xia;Yixiang Huang;Chengjin Qin;Dengyu Xiao;Liang Gong;Chengliang Liu;Wenliao Du
机械剩余使用寿命（RUL）预测在现代工业维护中发挥着关键作用。传统方法需要手动选择有用的特征，这需要先验知识并且缺乏对不同情况的适应性。此外，由于特征可能与不同阶段的退化过程具有不同的相关性，因此在整个生命周期中使用固定特征将限制预测性能。此外，大多数深度学习方法缺乏对特征全局信息的感知，而这对于 RUL 预测至关重要。为了解决这些问题，本文提出了一种具有单独门控机制和全局时间卷积网络（SGGTCN）的自适应特征利用方法。首先，提出了一种单独的门控机制，通过一系列设计的单独的门控残差模块，分别对每个特征内的时间信息进行自适应建模。其次，提出了一种自适应特征利用方法来评估和动态权衡特征重要性。第三，提出了全局时间卷积网络（GTCN）来建模和融合全局时间信息以进行全面的顺序建模。通过涡轮风扇发动机和轴承的两个预测案例研究验证了所提出方法的有效性和优越性。
Machinery remaining useful life (RUL) prediction plays a pivotal role in modern industrial maintenance. Traditional methods entail the manual selection of useful features, which requires prior knowledge and lack adaptability to diverse cases. Moreover, as features may have different relevance to the degradation process at various stages, the prognostic performance will be limited by the utilization of fixed features throughout the full lifetime. Additionally, most deep-learning methods lack the perception of global information of features, which is critical to RUL prediction. To tackle these issues, an adaptive feature utilization method with a separate gating mechanism and global temporal convolutional network (SGGTCN) is proposed in this article. First, a separate gating mechanism is proposed to adaptively model temporal information within each feature individually through a series of designed separate gated residual modules. Second, an adaptive feature utilization method is proposed to evaluate and dynamically weigh feature importance. Third, a global temporal convolutional network (GTCN) is proposed to model and fuse global temporal information for comprehensive sequential modeling. The effectiveness and superiority of the proposed method are validated by two prognostic case studies of turbofan engines and bearings.