A5102904169- Advanced Battery Technologies Research
- Advancements in Battery Materials
- Reliability and Maintenance Optimization
- Combustion and Detonation Processes
- Non-Destructive Testing Techniques
- Embedded Systems and FPGA Design
- Machine Fault Diagnosis Techniques
- Industrial Vision Systems and Defect Detection
- Smart Grid and Power Systems
- Power Systems and Renewable Energy
- Remote Sensing and LiDAR Applications
- Extraction and Separation Processes
- Robotic Path Planning Algorithms
- Smart Grid Security and Resilience
- Fetal and Pediatric Neurological Disorders
- Robotics and Sensor-Based Localization
- Electric Vehicles and Infrastructure
- Advanced battery technologies research
- Infrastructure Maintenance and Monitoring
- Advanced Algorithms and Applications
- Optimization and Search Problems
- 3D Surveying and Cultural Heritage
Hunan University of Technology
2024
Northeastern University
2024
Nanjing Forestry University
2023-2024
Xiamen University of Technology
2024
In the era of advancing technology, unmanned inspection robots have become indispensable for their efficiency, precision, and safety. Key to autonomous operation is Simultaneous Localization Mapping (SLAM) which allows navigate create maps unknown environments in real-time. This article explores integration SLAM with artificial intelligence, highlighting its role robotic navigation, localization, obstacle avoidance. Specifically, we delve into SLAM's principles, implementation LiDAR...
Lithium-ion battery health and remaining useful life (RUL) are essential indicators for reliable operation. Currently, most of the RUL prediction methods proposed lithium-ion batteries use data-driven methods, but length training data limits strategies. To solve this problem improve safety reliability batteries, a Li-ion method based on iterative transfer learning (ITL) Mogrifier long short-term memory network (Mogrifier LSTM) is proposed. Firstly, capacity degradation in source target...
Abstract Predicting the remaining useful life (RUL) of lithium batteries is crucial for predicting battery failure and health management. Accurately estimating RUL allows timely maintenance replacement that pose safety risks. To enhance reliability operations, this paper proposes a prediction model, attention mechanism-convolutional neural network (ACNN)-Mogrifier long short-term memory (LSTM)-maximum mean discrepancy (MMD), based on ACNN, Mogrifier LSTM, MMD Feature Transfer Learning....
Abstract Battery health monitoring is influenced by environmental and human factors, resulting in the presence of abnormal missing values detection data. These issues compromise accuracy subsequent life prediction fault diagnosis. To address this problem, we propose a deep learning-based method for cleaning battery anomalies imputing Initially, optimize Variational Modal Decomposition using Osprey Optimization Algorithm to minimize influence continuous discharge processes on local anomaly...
Abstract The accurate prediction of the Remaining Useful Life (RUL) lithium-ion batteries can significantly enhance safety and reliability these batteries, thereby reducing operational risks. However, numerous existing methodologies operate under assumption that both training testing data adhere to same distribution pattern, hindering application successful laboratory-based models different target batteries. Hence, this study introduces a transfer learning model for predicting battery life,...
This study introduced an innovative approach for detecting structural anomalies in road manhole covers using structured light cameras. Efforts have been dedicated to enhancing data quality by commencing with the acquisition and preprocessing of point cloud from real-world cover scenes. The RANSAC algorithm is subsequently employed extract plane determine height structure. In presence non-planar exhibiting abnormal heights, DBSCAN harnessed cluster segmentation, aiding identification...
Abstract To improve the early degradation detection capability of electrostatic monitoring system for rolling bearings, a performance evaluation method based on improved deep denoising autoencoder and adaptive density peak clustering (ADPC) is proposed in this paper. Firstly, fusion charge signal features with conventional time-domain, frequency-domain time–frequency-domain constitutes characteristic parameter set indicating status bearings. Then, order to feature extraction ability DAE,...
Motivation: Fetal MRI is important in clinical and scientific applications but prone to motion artifacts. Automated image quality assessment (IQA) assists data acquisition subsequent analyses. However, training neural networks for IQA requires labor-intensive manual annotation. Goal(s): To develop a model fetal that doesn't require labels. Approach: A network trained determine the orientation of 2D T2-weighted images. The variation recognition (ORN) inferences central images brain stack used...