No abstract

Deep learning has attracted intense interest in Prognostics and Health Management (PHM), because of its enormous representing power, automated feature learning capability and best-in-class performance in solving complex problems. This paper surveys recent advancements in PHM methodologies using deep learning with the aim of identifying research gaps and suggesting further improvements. After a brief introduction to several deep learning models, we review and analyze applications of fault detection, diagnosis and prognosis using deep learning. The survey validates the universal applicability of deep learning to various types of input in PHM, including vibration, imagery, time-series and structured data. It also reveals that deep learning provides a one-fits-all framework for the primary PHM subfields: fault detection uses either reconstruction error or stacks a binary classifier on top of the network to detect anomalies; fault diagnosis typically adds a soft-max layer to perform multi-class classification; prognosis adds a continuous regression layer to predict remaining useful life. The general framework suggests the possibility of transfer learning across PHM applications. The survey reveals some common properties and identifies the research gaps in each PHM subfield. It concludes by summarizing some major challenges and potential opportunities in the domain.

No abstract

No abstract

Abstract-High-dimensional data streams are becoming increasingly ubiquitous in industrial systems. Efficient detection of system faults from these data can ensure the reliability and safety of the system. The difficulties brought about by high dimensionality and data streams are mainly the "curse of dimensionality" and concept drifting, and one current challenge is to simultaneously address them. To this purpose, this paper presents an approach to fault detection from nonstationary highdimensional data streams. An angle-based subspace anomaly detection approach is proposed to detect low-dimensional subspace faults from high-dimensional datasets. Specifically, it selects fault-relevant subspaces by evaluating vectorial angles and computes the local outlier-ness of an object in its subspace projection. Based on the sliding window strategy, the approach is further extended to an online mode that can continuously monitor system states. To validate the proposed algorithm, we compared it with the local outlier factor-based approaches on artificial datasets and found the algorithm displayed superior accuracy. The results of the experiment demonstrated the efficacy of the proposed algorithm. They also indicated that the algorithm has the ability to discriminate low-dimensional subspace faults from normal samples in high-dimensional spaces and can be adaptive to the time-varying behavior of the monitored system. The online subspace learning algorithm for fault detection would be the main contribution of this paper.

The first off-on probe, Mito-TRFS, for imaging the mitochondrial thioredoxin reductase (TrxR2) in live cells was reported. In a cellular model of Parkinson's disease (PD), Mito-TRFS staining discloses a drastic decline of the TrxR2 activity, providing a mechanistic link of TrxR2 dysfunction to the etiology of PD.

This paper presents an unsupervised, density-based approach to anomaly detection. The purpose is to define a smooth yet effective measure of outlierness that can be used to detect anomalies in nonlinear systems. The approach assigns each sample a local outlier score indicating how much one sample deviates from others in its locality. Specifically, the local outlier score is defined as a relative measure of local density between a sample and a set of its neighboring samples. To achieve smoothness in the measure, we adopt the Gaussian kernel function. Further, to enhance its discriminating power, we use adaptive kernel width: in high-density regions, we apply wide kernel widths to smooth out the discrepancy between normal samples; in low-density regions, we use narrow kernel widths to intensify the abnormality of potentially anomalous samples. The approach is extended to an online mode with the purpose of detecting anomalies in stationary data streams. To validate the proposed approach, we compare it with several alternatives using synthetic datasets; the approach is found superior in terms of smoothness, effectiveness and robustness. A further experiment on a real-world dataset demonstrated the applicability of the proposed approach in fault detection tasks.

Cerebral ischemia/reperfusion (I/R) is common and intractable in the clinic, associated with the outburst of reactive oxygen species (ROS) in mitochondria. Although numerous research studies have been conducted to prove the protective-effect roles of glutathione (GSH) in this event, the changes in GSH concentrations in living cells remain largely unexplained, and there is scarce evidence by fluorescence imaging for its roles. Herein we have designed and synthesized two distinctive “off-on” near-infrared (NIR) fluorescent probes BCy-SeSe and BCy-SS based on a new fluorophore BCy-Keto for specific response to mitochondrial GSH changes during the cerebral I/R process. Both of them exhibit powerful targeting capability in mitochondria and excellent photophysical properties toward endogenous GSH with high selectivity and sensitivity. In contrast to BCy-SS, BCy-SeSe was screened for biological application on account of its faster response rate. We have utilized BCy-SeSe to real-time image GSH during the cerebral I/R process in living cells and the mice focal cerebral ischemia model (middle cerebral artery occlusion, MCAO), and these intensive studies revealed that low GSH levels were associated with aggravation of apoptosis and cerebral infarction. Pretreatment with GSH synthase inhibitor aggravates damage while GSH-ester alleviates damage, confirming that GSH is effective on the cerebrum for protection from I/R. All the results demonstrated that the probes were powerful tools for investigating mitochondrial GSH during the I/R process in living cells and in vivo.