A5017052151- Drilling and Well Engineering
- AI in cancer detection
- Medical Imaging and Analysis
- Hydraulic Fracturing and Reservoir Analysis
- Image and Object Detection Techniques
- Optical Systems and Laser Technology
- Medical Image Segmentation Techniques
- Concrete Corrosion and Durability
- Radiomics and Machine Learning in Medical Imaging
- Non-Destructive Testing Techniques
- Infrastructure Maintenance and Monitoring
- Flow Measurement and Analysis
- Reservoir Engineering and Simulation Methods
- Advanced Sensor and Control Systems
- Oil and Gas Production Techniques
Central South University
2024-2025
Crack detection at the pixel level across complex scenarios (structural interference and adverse working conditions) is a critical consideration in maintenance of ballastless track slab (BTS). Although existing deep learning models achieve acceptable accuracy on cracks with monotonous background, ground truth high labor cost inevitable their performance may fall far below theoretical bounds or even cause “all‐black images.” A hybrid algorithm based synthetic data from digital twin model...
The accurate prediction of post-refracture production can be great value in the selection target wells for refracturing. Given that from yields time-series data, deep neural networks have been utilized making these predictions. Conventional networks, including recurrent network and long shortterm memory network, often fail to effectively capture long-range dependencies, which is particularly evident tasks such as forecasting oil well over periods extending up 36 years. To overcome this...
<title>Abstract</title> Accurate grouting flow measurement is critical for optimizing construction quality and reducing material waste in geotechnical engineering. While electromagnetic flowmeters are widely used, their precision deteriorates significantly under low-flow conditions. This study proposes a laser ranging-based method to address this limitation by analyzing slurry liquid level fluctuations mixing drums. Through theoretical modeling, indoor experiments, numerical simulations, the...
Accurate grouting flow measurement is critical for optimizing construction quality and reducing material waste in geotechnical engineering. While electromagnetic flowmeters are widely used, their precision deteriorates significantly under low-flow conditions. This study proposes a laser ranging-based method to address this limitation by analyzing slurry liquid level fluctuations mixing drums. Through theoretical modeling, indoor experiments, numerical simulations, the fluctuation patterns...
Abstract The accurate prediction of post-fracturing production for re-fractured wells is crucial selecting suitable targets re-fracturing. Given that the essentially time series data, this study aims to provide an deep neural network approach wells. Traditional networks, such as Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM), are not adept at capturing long-range dependencies. To address limitation, a new Transformer Variant Prediction Production Re-fractured Oil Wells...