A5082362303- Model Reduction and Neural Networks
- Fluid Dynamics and Vibration Analysis
- Nuclear Engineering Thermal-Hydraulics
- Fluid Dynamics and Turbulent Flows
- Maritime Navigation and Safety
- Autonomous Vehicle Technology and Safety
- Global trade and economics
- Computational Physics and Python Applications
- Probabilistic and Robust Engineering Design
- Ship Hydrodynamics and Maneuverability
- Vehicle Dynamics and Control Systems
- Advanced Algorithms and Applications
- Fault Detection and Control Systems
- Target Tracking and Data Fusion in Sensor Networks
- Transportation Planning and Optimization
- Maritime Transport Emissions and Efficiency
- International Business and FDI
- Meteorological Phenomena and Simulations
- Oil and Gas Production Techniques
- Modeling and Simulation Systems
- Advanced Data Storage Technologies
- Advanced Decision-Making Techniques
- Advanced Measurement and Detection Methods
- Tensor decomposition and applications
- Traffic Prediction and Management Techniques
Swansea University
2022-2023
Chang'an University
2020
Communication University of China
2013
Abstract This paper presents a new nonlinear non‐intrusive reduced‐order model (NL‐NIROM) that outperforms traditional proper orthogonal decomposition (POD)‐based reduced order (ROM). improvement is achieved through the use of auto‐encoder (AE) and self‐attention based deep learning methods. The novelty this work it uses stacked (SAE) network to project original high‐dimensional dynamical systems onto low dimensional subspace predict fluid dynamics using an method. introduces reduction...
Nowadays, maritime transportation has become one of the most important ways international trade. However, with increase in ship transportation, complex environment led to frequent traffic accidents, causing huge economic losses and safety hazards. For ships collision avoidance route planning can be achieved by predicting ship’s trajectory, which give crews warning avoid dangers. How predict trajectory more accurately is great significance for risk avoidance. existing prediction models suffer...
This paper presents a new data-driven non-intrusive reduced-order model(NIROM) that outperforms the traditional Proper orthogonal decomposition (POD) based reducedorder model. is achieved by using Auto-Encoder(AE) and attention-based deep learning methods. The novelty of present work lies in it uses Stacked AutoEncoder(SAE) network to project original high-dimensional dynamical systems onto low dimensional nonlinear subspace predict fluid dynamics an attentionbased method. A model reduction...
Developing a human-like autonomous driving system has gained increasing amounts of attention from both technology companies and academic institutions, as it can improve the interpretability acceptance system. Planning safe obstacle avoidance trajectory is one critical issues for development vehicles (AVs). However, when designing automatic systems, few studies have focused on characteristics human drivers. This paper aims to develop an planning tracking model AVs that consistent with...
“Port–hinterland synergy” means the development of port and hinterland should promote each other. The “dual circulation” pattern indicates requirement exploring domestic transportation demand promoting integration between ports hinterlands. However, current research on synergy level hinterlands is not enough to meet needs constructing a pattern, few studies have explored influencing factors port–hinterland directly, especially in context new circulation”. After investigating synergetic...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
In this paper, we introduce a tensor neural network based machine learning method for solving the elliptic partial differential equations with random coefficients in bounded physical domain. With help of product structure, can transform high-dimensional integrations functions to one-dimensional which be computed classical quadrature schemes high accuracy. The complexity its calculation reduced from exponential scale polynomial scale. corresponding is designed parametric equations. Some...
As cultural life becomes rich,people have increasing demands for stage effects on performances.In some top grade sites and entertainment venues,hydraulic lift stages replace traditional stationary the sake of creating lively three-dimensional performance effects.However, hydraulic system is relatively huge.It’s not easy to check out location fault quickly, which makes efficiency resolving low. Based simulation circuit system,by means collecting,transforming analyzing pressure flow signal...
Abstract Background In recent years, the frequent occurrence of offshore oil leakage has increased risk pollution. According to statistics, in 1970s, there were two tanker accidents every week world. The American “Tory Canyon” drowned English Channel after hitting a rock 1967, and “Exxon Valdez” ran aground 1989. Oil had significant impact on marine environment, economy human health. Therefore, we must focus safety transportation port, so as protect mental health property crew environment....