A5028856836- Mechanical Behavior of Composites
- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- Structural Response to Dynamic Loads
- Robotics and Sensor-Based Localization
- Structural Behavior of Reinforced Concrete
- Multimodal Machine Learning Applications
- Additive Manufacturing and 3D Printing Technologies
- Industrial Vision Systems and Defect Detection
- Cellular and Composite Structures
- Robotic Path Planning Algorithms
- Domain Adaptation and Few-Shot Learning
- Advanced Manufacturing and Logistics Optimization
- Infrastructure Maintenance and Monitoring
- Structural Load-Bearing Analysis
- 3D Surveying and Cultural Heritage
- Aluminum Alloys Composites Properties
- Composite Structure Analysis and Optimization
Henan Polytechnic University
2024
PLA Army Engineering University
2018-2023
Abstract Compared with the resin‐based composite laminates, fiber metal laminates (FMLs) have superior impact resistance. In this study, investigations were made to reveal effects of stacking sequence on low‐velocity failure mechanisms and energy dissipation characteristics carbon reinforced plastics (CFRP)/Al hybrid same areal density. Experiments carried out characterize typical mechanical responses. Failure morphologies evaluated by X‐ray computed tomography scanning techniques. Then...
Most real-time semantic segmentation networks use shallow architectures to achieve fast inference speeds. This approach, however, limits a network’s receptive field. Concurrently, feature information extraction is restricted single scale, which reduces the ability generalize and maintain robustness. Furthermore, loss of image spatial details negatively impacts accuracy. To address these limitations, this paper proposes Multiscale Context Pyramid Pooling Spatial Detail Enhancement Network...
While the performance of state-of-the-art point-based VSLAM (vision simultaneous localization and mapping) systems in well textured sequences is impressive, their poorly situations not satisfactory enough. A sensible alternative or addition to consider lines. In this paper, we propose a novel line-assisted algorithm (LAP-SLAM). Our uses lines without descriptor matching, are used assist computation conducted by points. To best our knowledge, paper proposes new way include line information...
Abstract In this study, the axial crushing behavior of aluminum/carbon fiber reinforced plastic (CFRP) hybrid tubes are systematically investigated numerically based on a three‐dimensional (3D) progressive damage model. Experiments concerning with 1/1 and 2/1 lay‐up configurations performed first to validate numerical Then, effects chamfer at end, stacking configuration, aluminum‐CFRP bonding state thickness ratio individual layers energy absorption characteristics aluminum/CFRP further...
Abstract In this study, the flexural bearing capacity and failure mechanism of carbon fiber-reinforced aluminum laminate (CARALL) beams with a double-channel cross-section 3/2 laminated configuration were experimentally numerically studied. Two types specimens using different fiber layup configurations ([0°/90°/0°] 3 [45°/0°/−45°] ) fabricated pressure molding thermal curing forming process. The CARALL subjected to static three-point bending tests determine their behaviors in terms ultimate...
Road detection is an important part of the environment perception technology unmanned vehicles. Using computer vision to achieve semantic segmentation environmental scenes one key ensure safe driving In this paper, a hybrid autoencoder model combining sparse and denoising proposed. The uses conduct encoding use robust encoding. way, features learned by are more conducive for segmentation. Through deep rich structure model, optimized selection image semantics can be achieved, further improve...