A5036179171- Anatomy and Medical Technology
- Machine Fault Diagnosis Techniques
- Reliability and Maintenance Optimization
- Soft Robotics and Applications
- Advanced Battery Technologies Research
- Image and Signal Denoising Methods
- Ultrasonics and Acoustic Wave Propagation
- Thermography and Photoacoustic Techniques
- Surgical Simulation and Training
- Smart Grid and Power Systems
- Energy Load and Power Forecasting
- Calibration and Measurement Techniques
Tianjin University
2024
Zhejiang University of Technology
2020-2022
Increasing machine learning methods are being applied to infrared non-destructive assessment for internal defects of composite materials. However, most them extract only linear features, which is not in accord with the nonlinear characteristics data. Moreover, limited images tend restrict data analysis capabilities methods. In this work, a novel generative kernel principal component thermography (GKPCT) method proposed defect detection carbon fiber reinforced polymer (CFRP) composites....
Abstract Background Accurately estimating the 6D pose of snake‐like wrist‐type surgical instruments is challenging due to their complex kinematics and flexible design. Methods We propose ERegPose, a comprehensive strategy for precise estimation. The consists two components: ERegPoseNet, an original deep neural network model designed explicit regression instrument's pose, annotated in‐house dataset simulated operations. To capture rotational features, we employ Single Shot multibox Detector...
In this work, a classification and regression tree (CART) based extreme gradient boosting (XGBoost) model, simply denoted as XCART, is proposed to predict the lithium-ion batteries remaining useful life (RUL). First, fluctuations in RUL series are regarded inherent characteristics, voltage which have similar extracted important health indicators (HI). Then, HIs selected by feature importance indicator of XCART. After that, XCART used learn acquire prediction results. Experiments on NASA...
Accurate wind power forecasting plays an increasingly important role in the field of but still intractable practice. In order to improve accuracy forecasting, a novel model based on squeeze and excitation network (SENet) embedded dual-channel is proposed. The mechanism integrates convolutional neural gated recurrent unit, both which can be used without interfering with each other. SENet increase attention features, thus improving efficiency. Compared single model, proposed has better feature...