4.8 Article

Sparse Hierarchical Parallel Residual Networks Ensemble for Infrared Image Stream-Based Remaining Useful Life Prediction

期刊

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 19, 期 10, 页码 10613-10623

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2022.3229493

关键词

Degradation; Feature extraction; Streaming media; Residual neural networks; Ensemble learning; Computer architecture; Kernel; Hierarchical parallel residual network (HPRN); infrared image stream-based prognostics; remaining useful life (RUL) prediction; sparse ensemble

向作者/读者索取更多资源

Infrared thermography is used for contactless machine health monitoring by capturing real-time degradation temperature information. This article introduces a sparse hierarchical parallel residual networks ensemble (SHPRNE) method to address the challenge of multiscale characteristics and spatiotemporal degradation discrepancy in infrared images. The proposed method utilizes parallel multiscale kernels and a hierarchical residual connection procedure to capture complementary degradation patterns and promote interactivity between different levels of features. Additionally, a sparse ensemble algorithm, integrated with network pruning and local minima perpetuation, is used to derive diverse networks and improve generalization.
Infrared thermography captures real-time degradation temperature information, facilitating noncontact machine health monitoring. However, the inherent multiscale characteristics and spatiotemporal degradation discrepancy in infrared images pose a challenge in learning discriminative degradation features and adaptive prognostic analytics. This article presents a sparse hierarchical parallel residual networks ensemble (SHPRNE) method to tackle this challenge. First, the hierarchical parallel residual network (HPRN) leverages parallel multiscale kernels to capture complementary degradation patterns separately and embeds a hierarchical residual connection procedure to facilitate the interactivity between coarse-to-fine level features. Moreover, SHPRNE develops a sparse ensemble algorithm integrated with a synergy of network pruning and local minima perpetuation to derive diverse HPRNs while alleviating the parameter storage budget. Pruned HPRNs with varying sparsity and local minima are further integrated into an ensemble learner with higher generalization. Case studies on two infrared image datasets are conducted to demonstrate the effectiveness and superiority of the proposed method.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据