A5019373327- Fault Detection and Control Systems
- Machine Fault Diagnosis Techniques
- Advanced Computational Techniques and Applications
- Identification and Quantification in Food
- Genomics and Phylogenetic Studies
- Advanced Data Processing Techniques
- Engineering Diagnostics and Reliability
- Anomaly Detection Techniques and Applications
- Software Reliability and Analysis Research
- Optimization and Search Problems
- Satellite Communication Systems
- Aquaculture disease management and microbiota
- Advanced Decision-Making Techniques
- Gear and Bearing Dynamics Analysis
- Genetic diversity and population structure
- Advanced Algorithms and Applications
- AI-based Problem Solving and Planning
- Musculoskeletal pain and rehabilitation
- Ichthyology and Marine Biology
- Non-Destructive Testing Techniques
- Biomedical Text Mining and Ontologies
- Reliability and Maintenance Optimization
- Machine Learning in Healthcare
- Advanced Sensor and Control Systems
- Engineering and Test Systems
Harbin Institute of Technology
2013-2024
Yale University
2010-2024
VA Connecticut Healthcare System
2023-2024
Veterans Health Administration
2023
Chinese Academy of Sciences
2021
Hefei Institutes of Physical Science
2021
Institute of Plasma Physics
2021
University of Macau
2021
University of Science and Technology of China
2021
Hefei University of Technology
2020
The data-driven diagnosis methods based on conventional machine-learning techniques have been widely developed in recent years. However, the assumption of that training and test data should be identically distributed is usually unsatisfied actual scenario. While there are several existing works studied to construct models by transfer learning methods, most them only focused from a single source. Actually, how discover effective general knowledge multiple related source domains further...
Recent works suggest that using knowledge transfer strategies to tackle cross-domain diagnosis problems is promising for achieving engineering diagnosis. This article presents a scheme rolling bearing under challenging domain generalization scenario, in which more potential discrepancies among multiple source domains are eliminated and only normal samples of the target available during training stage. To achieve sufficient performance, combining some priori deep network fault (DDGFD)...
Abstract Background B7-H3, an immune-checkpoint molecule and a transmembrane protein, is overexpressed in non-small cell lung cancer (NSCLC), making it attractive therapeutic target. Here, we aimed to systematically evaluate the value of B7-H3 as target NSCLC via T cells expressing B7-H3-specific chimeric antigen receptors (CARs) bispecific killer engager (BiKE)-redirected natural (NK) cells. Methods We generated CAR B7-H3/CD16 BiKE derived from anti-B7-H3 antibody omburtamab that has been...
This paper proposes a combined method to detect and isolate small faults of actuators in closed-loop control systems. The fault with some tiny magnitude (not larger than the disturbances) is mainly considered for nonlinear system subjected model uncertainties, disturbances, noises. basic idea our study use model-based decouple possible disturbances faults, then, appeal computing intelligence further reduce influence remaining uncertainties. Specifically, proposed approach an extension...
The cross-domain fault diagnosis problem based on deep domain adaptation (deep DA) has gained great attention in recent years. However, a required but not easily satisfied assumption many researches that the label space of source and target should be identical limits their applications practice. In industrial reality, may only subset domain, which is defined as partial DA scenario. Focusing this scenario, paper proposes novel method named instance weighted mean maximum discrepancy (IWMMD). A...
Satellite range scheduling with the priority constraint is one of most important problems in field satellite operation. This paper proposes a station coding based genetic algorithm to solve this problem, which adopts new chromosome encoding method that arranges tasks according ground ID. The contributes reducing complexity conflict checking and resolving, helps improve ability find optimal resolutions. Three different selection operators are designed match strategy, namely random selection,...
To understand the phylogenetic position of Larimichthys polyactis within family Sciaenidae and phylogeny this family, organization mitochondrial genome small yellow croaker was determined herein. The complete, 16,470 bp long, contains 37 genes (13 protein-coding, 2 ribosomal RNA 22 transfer genes), as well a control region (CR), in other bony fishes. Comparative analysis initiation/termination codon usage protein-coding Percoidei species, indicated that COI entails an ATG/AGA different from...
This paper describes a combined genetic algorithm for selecting and scheduling tasks of agile earth observing satellites (AEOS). kind satellite has three degrees freedom acquiring images, giving opportunities more efficient use the imaging capabilities. But selection observations becomes significantly difficult, due to larger search space potential solutions. Hence, is highly combinatorial problem. Inspired by successful commercial applications evolutionary algorithms in domains, this...
Hydraulic pump is a driving device of the hydraulic system, always working under harsh operating conditions, its fault diagnosis work necessary for smooth running system. However, it difficult to collect sufficient status information in practical processes. In order achieve with poor information, novel method that based on Symbolic Perceptually Important Point (SPIP) and Hidden Markov Model (HMM) proposed. important point technology firstly imported into rotating machine diagnosis; applied...