A5057512648- Machine Fault Diagnosis Techniques
- Reliability and Maintenance Optimization
- Tissue Engineering and Regenerative Medicine
- Non-Destructive Testing Techniques
- Gear and Bearing Dynamics Analysis
- Electrospun Nanofibers in Biomedical Applications
- Liver Disease and Transplantation
- Liver Disease Diagnosis and Treatment
- Radio Frequency Integrated Circuit Design
- EEG and Brain-Computer Interfaces
- Superconducting and THz Device Technology
- Fault Detection and Control Systems
- VLSI and Analog Circuit Testing
- Anomaly Detection Techniques and Applications
- Microwave Engineering and Waveguides
- Engineering Diagnostics and Reliability
- Advanced machining processes and optimization
- Liver physiology and pathology
- Water Treatment and Disinfection
- Time Series Analysis and Forecasting
- Polyoxometalates: Synthesis and Applications
- Advanced Memory and Neural Computing
- Mesenchymal stem cell research
- Advanced Graph Neural Networks
- Chemical Analysis and Environmental Impact
South China University of Technology
2011-2025
University of Electronic Science and Technology of China
2023-2025
Guangdong University of Petrochemical Technology
2025
South China Normal University
2024
First Affiliated Hospital Zhejiang University
2020-2024
State Key Laboratory of Diagnosis and Treatment of Infectious Diseases
2020-2024
National Clinical Research Center for Digestive Diseases
2023-2024
Shenzhen University
2021-2024
Tsinghua University
2021-2024
Cornell University
2022-2023
This paper presents a new online detection approach for rolling bearing's incipient fault based on self-adaptive deep feature matching (SDFM). includes offline and stages. At the stage, health state assessment algorithm is first proposed singular value decomposition (SVD) Kurtosis criterion. Based results, kind of learning algorithm, i.e., stacked denoising autoencoder (SDAE), introduced to extract common features normal early state. Support vector data description (SVDD) applied establish...
This article tries to answer the two questions of bearings' remaining useful life (RUL) prediction with deep transfer learning: what bearing data in source domain contribute more learning and how quantify such contribution? From perspective sample-based interpretability, this proposes a new approach RUL prediction. First, time series clustering algorithm based on multiscale degradation similarity is proposed. Comprehensively considering geometry tendency characteristics sequences, can divide...
This article proposes a novel deep transfer learning-based online remaining useful life (RUL) approach for rolling bearings under unknown working condition. solves the following concerns: drift of condition would block data accumulation and raise bias in prediction model, bearing merely has early fault when activating RUL prediction, failing to conduct learning from offline data. First, new time series recursive forecasting model is constructed generate pseudovalues via fusing prior...
The development of Internet Things technology provides abundant data resources for prognostics health management industrial machinery, and data-driven methods have shown their powerful ability in the field fault diagnosis. However, these several limitations: 1) Using less labeled to obtain higher accuracy is a challenging task, which limits application diagnostic models practical applications. 2) Physics-informed knowledge largely ignored during modeling process, contains wealth information...
In many applications, it is not easy to generate enough whole-life data for training a deep neural network, which may reduce the performance of health indicator (HI). To solve this problem, new HI construction method based on transfer learning proposed in article. First, multiscale domain-adversarial network extract representative features from collected under different working conditions. By introducing maximum mean discrepancy regularizer and Laplace regularizer, model can enhance...
An imidazolium-based hyper-crosslinked porous ionic polymer (IHPiP) immobilized phosphotungstic (PW) anions hybrid catalyst (IHPiP-PW) was synthesized based on a one-pot Friedel–Crafts alkylation and quaternization reaction, followed by anion exchange reaction. The obtained IHPiP-PW exhibited high specific surface area of 615 m2·g-1 containing plentiful hierarchical pores. effective in the oxidation 1-phenylethanol into acetophenone with H2O2 to give conversion 95.7%, quantitative...
Developing functional ductal organoids (FDOs) is essential for liver regenerative medicine. We aimed to construct FDOs with biliary tree networks in rat decellularized scaffolds (DLSs) primary cholangiocytes isolated from mouse bile ducts. The developed were dynamically characterized by assays and metabolomics bioprocess clarification. reconstructed DLSs retaining native structure bioactive factors expressing enriched biomarkers. Morphological assessment showed that tree-like structures...
Chlorinated compounds were generally present in the environment due to widespread use industry. A short-term study was performed evaluate effects of 1,1,1- trichloroethane (TCA) and triclocarban (TCC) on trichloroethene (TCE) removal a reactor fed with lactate as sole electron donor. Both TCA TCC inhibited TCE reduction, but had more pronounced effect compared TCA. The TCE-reducing culture, which never been exposed before, reductively dechlorinated 1,1-dichloroethane (DCA). Below 15 µM,...
Abstract Hepatitis B virus‐related acute‐on‐chronic liver failure (HBV‐ACLF) is a syndrome with high short‐term mortality. The mechanism of the transcription factor ETS2 in ACLF remains unclear. This study aimed to clarify molecular basis pathogenesis. Peripheral blood mononuclear cells from patients HBV‐ACLF ( n = 50) were subjected RNA sequencing. Transcriptome analysis showed that expression was significantly higher than chronic diseases and healthy subjects (all p < 0.001)....
Aiming at the online detection problem of rolling bearings, limited amount target bearing data leads to insufficient model in training and feature representation. It is difficult for construct an accurate decision boundary. To solve problem, a multi-scale robust anomaly method based on enhancement technology proposed this paper. Firstly, are transformed into multiple subspaces through technology. Then, prototype clustering introduced enhance robustness features representation under framework...
Acute-on-chronic liver failure (ACLF) is clinical syndrome with high mortality rate. This study aimed to perform detailed transcriptomic analysis in cirrhosis–based ACLF rats elucidate pathogenesis. was induced by combined porcine serum D-galactosamine and lipopolysaccharide. Gene expression profile of tissues from generated transcriptome sequencing reveal the molecular mechanism. successfully developed typical characteristics. Total 2,354/3,576 differentially expressed genes were identified...
Vector-based dynamic IR-drop analysis of the entire vector set is infeasible due to long runtime. In this paper, we use machine learning perform vector-based IR drop prediction for all logic cells in circuit. We extract important features, such as toggle counts and arrival time, directly from simulation waveform so that can quickly. also propose a feature engineering method, density map, increase correlation by 0.1. Our method scalable because dimension fixed (72), independent design size...