A5100409861- Enhanced Oil Recovery Techniques
- Hydraulic Fracturing and Reservoir Analysis
- Petroleum Processing and Analysis
- Hydrocarbon exploration and reservoir analysis
- Face and Expression Recognition
- Reservoir Engineering and Simulation Methods
- Face recognition and analysis
- Fault Detection and Control Systems
- Drilling and Well Engineering
- Underwater Vehicles and Communication Systems
- UAV Applications and Optimization
- Advanced Sensor and Control Systems
- Smart Grid Security and Resilience
- Robotics and Sensor-Based Localization
- Advanced Measurement and Detection Methods
- Coal Properties and Utilization
- Industrial Technology and Control Systems
- Advanced Algorithms and Applications
- Infrared Target Detection Methodologies
- Adaptive Control of Nonlinear Systems
- Oil and Gas Production Techniques
- Optical Systems and Laser Technology
- Combustion and flame dynamics
- Vibration and Dynamic Analysis
- Simulation and Modeling Applications
Shanghai Ocean University
2012-2025
State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation
2014-2025
Qingdao Agricultural University
2025
Hainan University
2024-2025
Wuhan Sports University
2025
Wuhan University
2022-2025
Halliburton (United Kingdom)
2025
Nanjing University of Science and Technology
2008-2025
Kunming University of Science and Technology
2024
Northeast Petroleum University
2023-2024
Convolutional sparse coding (CSC) can model local connections between image content and reduce the code redundancy when compared with patch-based coding. However, CSC needs a complicated optimization procedure to infer codes (i.e., feature maps). In this brief, we proposed convolutional auto-encoder (CSAE), which leverages structure of AE incorporates max-pooling heuristically sparsify maps for learning. Together competition over channels, simple sparsifying strategy makes stochastic...
Data augmentation (DA) has been widely utilized to improve generalization in training deep neural networks. Recently, human-designed data gradually replaced by automatically learned policy. Through finding the best policy well-designed search space of augmentation, AutoAugment can significantly validation accuracy on image classification tasks. However, this approach is not computationally practical for large-scale problems. In paper, we develop an adversarial method arrive at a...
Abstract In this paper, we consider a state estimation problem. problem, sensor measures the of linear discrete‐time system and sends measurements to an estimator via packet‐dropping communication link. We are concerned with effect Denial‐of‐Service (DoS) attacks on stability system, particularly focus how examine whether channel is under DoS attack or not as well defend accordingly, if defense possible. formulate detection problem hypothesis testing provided that statistics known priori ....
A major progress in deep multilayer neural networks (DNNs) is the invention of various unsupervised pretraining methods to initialize network parameters which lead good prediction accuracy. This paper presents sparseness analysis on hidden unit process. In particular, we use L1 -norm measure and provide some sufficient conditions for that leads with respect popular models-such as denoising autoencoders (DAEs) restricted Boltzmann machines (RBMs). Our experimental results demonstrate when are...
We consider an unmanned aerial vehicle (UAV) assisting data collection from multiple sensor nodes (SNs). provide a completion time minimization design via jointly deciding the UAV trajectory and SN assignment scheme. In particular, we first characterize fundamental features of joint optimal solution to formulated problem. On one hand, is proved following successive-hover-fly (SHF) structure. Namely, in solution, successively visits hovering points performs with designated duration, while...
In a wind farm, power system is key to maintaining continuous generation of point energy. Since Zero-Dynamics attack poses major risk future farms, investigation on the effect against systems has both theoretical and practical importance. this paper, we consider scenario in which subject chain. Firstly, transform semi-direct D-PMSG into an equivalent circuit establish mathematical model under attack. Then, analyze prove advantages limitations by divide equation state stable part unstable...
Abstract Enhanced oil recovery by means of polymer flooding is considered as an important technology for the strategic development offshore oilfields in China. The implementation requires overcoming several major technical problems caused largely absence a fresh water source and limited space on platform. A pilot test was conducted SZ36-1 Oilfield located Bohai Bay, mentioned above were solved through (1) hydrophobically associating tolerant to salts brine produced (2) portable automatic...
Abstract Surfactant Polymer flooding (SP flooding) has drawn more attention than Alkaline (ASP in China due to the difficulty of demulsification and scale formation problem from alkali ASP. Traditionally, primary requirement for surfactant SP is lowest interfacial tension (IFT). However, core tests performed a series heterogeneous models have demonstrated there exist optimized IFT polymer viscosity flooding, which can maximize oil recovery formation. The low value but not possible value, at...
This paper proposes a low-complexity frequency-domain turbo equalizer (FDTE) combined with phase rotation compensation and soft successive interference cancellation (SSIC) for single carrier multiple-input multiple-output (MIMO) underwater acoustic (UWA) communications. Different from existing time-domain equalizers in MIMO UWA systems, the proposed receiver implements equalization frequency domain to combat severe inter-symbol (ISI) employs layered structure cope unbalanced channels. Soft,...
Single image dehazing is a notoriously challenging task in processing due to the numerous unknown factors involved. Most existing methods are based on physical models of haze formation process. However, real-world scenes cannot be accurately mathematically modeled existence various unquantifiable scene. Therefore, often perform poorly complex scenes. In this paper, we propose novel black-box equation. equation, modelled as an additional interference layer, without explicitly reasoning about...