A5100651291- Fuel Cells and Related Materials
- Textile materials and evaluations
- Electrocatalysts for Energy Conversion
- Geotechnical Engineering and Analysis
- Natural Language Processing Techniques
- Advancements in Solid Oxide Fuel Cells
- Geotechnical Engineering and Underground Structures
- Gear and Bearing Dynamics Analysis
- Machine Fault Diagnosis Techniques
- Topic Modeling
- Advanced machining processes and optimization
- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
- Epigenetics and DNA Methylation
- Air Quality and Health Impacts
- Metal and Thin Film Mechanics
- Domain Adaptation and Few-Shot Learning
- Tunneling and Rock Mechanics
- Anomaly Detection Techniques and Applications
- Transition Metal Oxide Nanomaterials
- Air Quality Monitoring and Forecasting
- Cancer-related gene regulation
- Membrane-based Ion Separation Techniques
- Safety Warnings and Signage
- Traffic and Road Safety
Microsoft Research (United Kingdom)
2025
University of Science and Technology Beijing
2023-2024
China Railway Group (China)
2023-2024
Shenyang University of Technology
2022-2024
Microsoft (Finland)
2023-2024
Shandong University of Technology
2022-2024
Changchun University of Science and Technology
2023
Hebei University
2023
Shandong University
2023
Agency for Science, Technology and Research
2023
The confining pressure has a great effect on the internal force of tunnel. During construction, which crucial impact tunnel construction changes due to variation groundwater level and applied load. Therefore, safety tunnels must have magnitude accurately estimated. In this study, complete time axis was obtained through high-frequency field monitoring, data are segmented into training set testing set. Using GRU RNN models, prediction model established, results were analyzed. indicate that...
Objective The visual guiding system, as a tunnel traffic safety improvement method by using facilities to actively guide driving safely, has been widely used in countries with many tunnels, recent years. This paper aims quantitatively study the comprehensive evaluation of system which certain engineering application value and can provide support for quantitative optimal design safety.
The construction of large-diameter shield tunnels underwater involves complex variations in water and earth load outside the tunnel segment, as well intricate mechanical responses. This study analyzes variation laws external loads, axial forces, bending moments acting on segment ring during assembly removal from tail. It accomplishes this through establishment an on-site monitoring system based Internet Things (IoT) proposes a Bayesian-genetic algorithm model to estimate pressure....
Document retrieval techniques form the foundation for development of large-scale information systems. The prevailing methodology is to construct a bi-encoder and compute semantic similarity. However, such scalar similarity difficult reflect enough impedes our comprehension results. In addition, this computational process mainly emphasizes global semantics ignores fine-grained relationship between query complex text in document. paper, we propose new method called $\textbf{Ge}$neration...
Document retrieval techniques form the foundation for development of large-scale information systems. The prevailing methodology is to construct a bi-encoder and compute semantic similarity. However, such scalar similarity difficult reflect enough impedes our comprehension results. In addition, this computational process mainly emphasizes global semantics ignores fine-grained relationship between query complex text in document. paper, we propose new method called Generation Augmented...
As a result of China’s urbanization, it has been common phenomenon that adjacent deep excavations were constructed near underground structures, which can have series detrimental effects on existing tunnels. Thus, is crucial to assess the tunnel response induced by overlying excavation, with aim maintaining safety and serviceability operating The shield idealized as an infinite beam lying upon three parameter Kerr-model vertical force equilibrium equation element established. Then,...
With the advancement of engineering techniques, underground shield tunneling projects have also started incorporating emerging technologies to monitor forces and displacements during construction operation phases tunnels. Monitoring devices installed on tunnel segment components generate a large amount data. However, due various factors, data may be missing. Hence, completion incomplete is imperative ensure utmost safety project. In this research, missing imputation technique utilizing...
The zoning excavation method is fully employed to control the deformation of foundation pits constructed in urban soft soil areas. However, similarities and differences forces deformations between excavated by zonal those conventional still need be further explored. In this study, was monitored analyzed taking a pit ‘New World’ project Hangzhou City as research object. measured results showed that pre-built diaphragm wall for first restricted wall. presence extensive construction unloading...
An ingenious yet effective strategy was applied to prepare P-based Li-argyrodites with Sb-based Li-argyrodite doping. The incorporation of Sn, Sb and I endows the novel ternary-doped Li 6 PS 5 Cl electrolyte much enhanced integrated performance.
The method of acoustic radiation signal detection not only enables contactless measurement but also provides comprehensive state information during equipment operation. This paper proposes an enhanced feature extraction network (EFEN) for fault diagnosis rolling bearings based on learning. EFEN comprises four main components: the data preprocessing module, selection module (IFSM), channel attention mechanism (CAMM), and convolutional neural (CNNM). Firstly, one-dimensional is transformed...
Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models. In this paper, we analyze the impact of low-rank updating, as implemented in LoRA. Our findings suggest that updating mechanism may limit ability LLMs to effectively learn and memorize new knowledge. Inspired by observation, propose called MoRA, which employs square matrix achieve high-rank while maintaining same number trainable parameters. To it, introduce corresponding non-parameter...
Wind turbine rolling bearings are crucial components for ensuring the reliability and stability of wind power systems. Their failure can lead to significant economic losses equipment downtime. Therefore, accurate diagnosis bearing faults is great importance. Although existing deep learning fault methods have achieved certain results, they still face limitations such as inadequate feature extraction capabilities, insufficient generalization complex working conditions, ineffective multi-scale...