Modern engineered systems generally work under complex operational conditions. However, most of the existing artificial intelligence (AI)-based prognostic methods still lack an effective model that ...can utilize operational conditions data for remaining useful life (RUL) prediction. This paper develops a novel prognostic method based on bidirectional long short-term memory (BLSTM) networks. The method can integrate multiple sensors data with operational conditions data for RUL prediction of engineered systems. The proposed architecture based on BLSTM networks includes three main parts: first, one BLSTM network is used to directly extract features hidden in the multiple raw sensors signals; second, another BLSTM network is employed to learn higher features from operational conditions signals and the learned features from the sensors signals; and, third, fully connected layers and a linear regression layer are stacked to generate the target output of the RUL prediction. Unlike other AI-based prognostic methods, the developed method can simultaneously model both sensors data and operational conditions data in a consolidated framework. The proposed approach is demonstrated through a case study on aircraft turbofan engines, and comparisons with other popular state-of-the-art methods are also presented.
A macroscopic 3D porous graphitic carbon nitride (g‐CN) monolith is prepared by the one‐step thermal polymerization of urea inside the framework of a commercial melamine sponge and exhibits improved ...photocatalytic water‐splitting performance for hydrogen evolution compared to g‐CN powder due to the 3D porous interconnected network, larger specific surface area, better visible light capture, and superior charge‐separation efficiency.
The impact of variation of Epstein-Barr virus (EBV) antibody titers before the development of nasopharyngeal carcinoma (NPC) is still unclear. We analyzed the fluctuations of antibodies against EBV ...before histopathological diagnosis to assess the risk of NPC and aimed to provide a reliable basis for screening in high risk populations.
This study was based on a population-based screening program in Sihui County in Guangdong Province of China. A total of 18,986 subjects were recruited in 1987 and 1992, respectively. Baseline and repeated serological tests were performed for IgA antibodies against EBV capsid antigen (VCA/IgA) and early antigen (EA/IgA). Follow-up until the end of 2007 was accomplished through linkage with population and health registers. Cox proportional hazards regression model was used to estimate the relative risk of NPC in association with EBV antibodies. Time-dependent receiver operating characteristic curve (ROC) analysis was used to further evaluate the predictive ability.
A total of 125 NPCs occurred during an average of 16.9 years of follow-up. Using baseline information alone or together with repeated measurements, serological levels of VCA/IgA and EA/IgA were significantly associated with increased risks for NPC, with a striking dose-response relationship and most prominent during the first 5 years of follow-up. Considering the fluctuant types of serological titers observed during the first three tests, relative risk was highest among participants with ascending titers of EBV VCA/IgA antibodies with an adjusted hazard ratio (HR) of 21.3 (95% confidence interval CI 7.1 to 64.1), and lowest for those with decreasing titers (HR = 1.5, 95% CI 0.2 to 11.4), during the first 5 years of follow-up. Time-dependent ROC analysis showed that VCA/IgA had better predictive performance for NPC incidence than EA/IgA.
Our study documents that elevated EBV antibodies, particularly with ascending titers, are strongly associated with an increased risk for NPC.
Electrocatalytic nitrogen reduction reaction (NRR) is a promising strategy for ammonia (NH3) production under ambient conditions. However, it is severely impeded by the challenging activation of the ...NN bond and the competing hydrogen evolution reaction (HER), which makes it crucial to design electrocatalysts rationally for efficient NRR. Herein, the rational design of bismuth (Bi) nanoparticles with different oxidation states embedded in carbon nanosheets (Bi@C) as efficient NRR electrocatalysts is reported. The NRR performance of Bi@C improves with the increase of Bi0/Bi3+ atomic ratios, indicating that the oxidation state of Bi plays a significant role in electrochemical ammonia synthesis. As a result, the Bi@C nanosheets annealed at 900 °C with the optimal oxidation state of Bi demonstrate the best NRR performance with a high NH3 yield rate and remarkable Faradaic efficiency of 15.10 ± 0.43% at −0.4 V versus RHE. Density functional theory calculations reveal that the effective modulation of the oxidation state of Bi can tune the p‐filling of active Bi sites and strengthen adsorption of *NNH, which boost the potential‐determining step and facilitate the electrocatalytic NRR under ambient conditions. This work may offer valuable insights into the rational material design by modulating oxidation states for efficient electrocatalysis.
An oxidation state modulation strategy is proposed to boost nitrogen reduction to ammonia. As a proof‐of‐concept, the surface oxidation of Bi species is tuned with the less occupied p orbital, which leads to stronger adsorption of *NNH and lower ΔG of the potential‐determining step. By optimizing Bi surface oxidation, superior nitrogen reduction reaction performance of Faradaic efficiency of 15.10 ± 0.43% is achieved.
2D graphitic carbon nitride (GCN) nanosheets have attracted tremendous attention in photocatalysis due to their many intriguing properties. However, the photocatalytic performance of GCN nanosheets ...is still restricted by the limited active sites and the serious aggregation during the photocatalytic process. Herein, a simple approach to produce holey GCN (HGCN) nanosheets with abundant in‐plane holes by thermally treating bulk GCN (BGCN) under an NH3 atmosphere is reported. These formed in‐plane holes not only endow GCN nanosheets with more exposed active edges and cross‐plane diffusion channels that greatly speed up mass and photogenerated charge transfer, but also provide numerous boundaries and thus decrease the aggregation. Compared to BGCN, the resultant HGCN has a much higher specific surface area of 196 m2 g−1, together with an enlarged bandgap of 2.95 eV. In addition, the HGCN is demonstrated to be self‐modified with carbon vacancies that make HGCN show much broader light absorption extending to the near‐infrared region, a higher donor density, and remarkably longer lifetime of charge carriers. As such, HGCN has a much higher photocatalytic hydrogen production rate of nearly 20 times the rate of BGCN.
An efficient etching process, thermal treatment of bulk graphitic carbon nitride under NH3 atmosphere, has been developed to synthesize holey graphitic carbon nitride (HGCN) nanosheets. The resultant HGCN exhibits significantly improved photocatalytic hydrogen production performance under visible light.
Recently, heteroatom‐doped three‐dimensional (3D) nanostructured carbon materials have attracted immense interest because of their great potential in various applications. Hence, it is highly ...desirable to exploit a simple, renewable, scalable, multifunctional, and general strategy to engineer 3D heteroatom‐doped carbon nanomaterials. Herein, a simple, eco‐friendly, general, and effective way to fabricate 3D heteroatom‐doped carbon nanofiber networks on a large scale is reported. Using this method, 3D P‐doped, N,P‐co‐doped, and B,P‐co‐doped carbon nanofiber networks are successfully fabricated by the pyrolysis of bacterial cellulose immersed in H3PO4, NH4H2PO4, and H3BO3/H3PO4 aqueous solution, respectively. Moreover, the as‐prepared N,P‐co‐doped carbon nanofibers exhibit good supercapacitive performance.
A simple, efficient, and general approach is developed for preparing cost‐effective, three‐dimensional, and large‐scale heteroatom‐doped carbon nanofibers, such as P‐doped, N,P‐co‐doped, and B,P‐co‐doped carbon nanofibers, by pyrolyzing bacterial cellulose (BC) previously immersed in H3PO4, NH4H2PO4, and H3BO3/H3PO4, respectively. Moreover, the as‐prepared N,P‐co‐doped carbon nanofibers exhibit good supercapacitive performance.
Many real‐world systems use mission aborts to enhance their survivability. Specifically, a mission can be aborted when a certain malfunction condition is met and a risk of a system loss in the case ...of a mission continuation becomes too high. Usually, the rescue or recovery procedure is initiated upon the mission abort. Previous works have discussed a setting when only one attempt to complete a mission is allowed and this attempt can be aborted. However, missions with a possibility of multiple attempts can occur in different real‐world settings when accomplishing a mission is really important and the cost‐related and the time‐wise restrictions for this are not very severe. The probabilistic model for the multiattempt case is suggested and the tradeoff between the overall mission success probability (MSP) and a system loss probability is discussed. The corresponding optimization problems are formulated. For the considered illustrative example, a detailed sensitivity analysis is performed that shows specifically that even when the system's survival is not so important, mission aborting can be used to maximize the multiattempt MSP.
•Epistemic uncertainty and CCFs are synthesized in reliability analysis of MSSs•D-S evidence theory is used to express the epistemic uncertainty in system•A modified β factor parametric model is ...introduced to model the multiple CCF groups•Developed method is shown to be efficient and practical.
With the increasing complexity and size of modern advanced engineering systems, the traditional reliability theory cannot characterize and quantify the complex characteristics of complex systems, such as multi-state properties, epistemic uncertainties, common cause failures (CCFs). This paper focuses on the reliability analysis of complex multi-state system (MSS) with epistemic uncertainty and CCFs. Based on the Bayesian network (BN) method for reliability analysis of MSS, the Dempster-Shafer (DS) evidence theory is used to express the epistemic uncertainty in system through the state space reconstruction of MSS, and an uncertain state used to express the epistemic uncertainty is introduced in the new state space. The integration of evidence theory with BN which called evidential network (EN) is achieved by adapting and updating the conditional probability tables (CPTs) into conditional mass tables (CMTs). When multiple CCF groups (CCFGs) are considered in complex redundant system, a modified β factor parametric model is introduced to model the CCF in system. An EN method is proposed for the reliability analysis and evaluation of complex MSSs in this paper. The reliability analysis of servo feeding control system for CNC heavy-duty horizontal lathes (HDHLs) by this proposed method has shown that CCFs have considerable impact on system reliability. The presented method has high computational efficiency, and the computational accuracy is also verified.
•Deep learning based semantic segmentation method with fully convolutional network is proposed.•Defect images are captured via a self-developed image acquisition equipment (MTI-200a).•The proposed ...method can rapidly and accurately recognize defects for metro shield tunnels.
The performance of traditional visual inspection by handcrafted features for crack and leakage defects of metro shield tunnel is hardly satisfactory nowadays because it is low-efficient to distinguish defects from some interference such as segmental joints, bolt holes, cables and manual marks. Based on deep learning (DL), this paper proposes a novel image recognition algorithm for semantic segmentation of crack and leakage defects of metro shield tunnel using hierarchies of features extracted by fully convolutional network (FCN). The defect images in training dataset and testing dataset are captured via a self-developed image acquisition equipment named Moving Tunnel Inspection (MTI-200a). After the establishment of image datasets, FCN models of crack and leakage are separately trained through several iterations of forward inference and backward learning. Semantic segmentation of defect images is implemented via the corresponding FCN models using two-stream algorithm, i.e. one stream is used to recognize the crack by sliding-window-assembling operation and the other is adopted for the leakage by resizing-interpolation operation. Compared with two frequently-used traditional methods, i.e. region growing algorithm (RGA) and adaptive thresholding algorithm (ATA), great superiority of the proposed method in terms of recognition results, inference time and error rates is shown based on four typical types of defect images which are crack-only image, leakage-only image, two-defect-nonoverlapping (TDN) image, two-defect-overlapping (TDO) image. The proposed method using DL can be employed to rapidly and accurately recognize defects for structure health monitoring and maintenance of metro shield tunnels.