A5100442075- Advanced Battery Technologies Research
- Advancements in Battery Materials
- Fault Detection and Control Systems
- Electric Vehicles and Infrastructure
- Reliability and Maintenance Optimization
- Advanced Battery Materials and Technologies
- Remote-Sensing Image Classification
- Advanced Algorithms and Applications
- Remote Sensing and Land Use
- Advanced DC-DC Converters
- Fuel Cells and Related Materials
- Multilevel Inverters and Converters
- Image Retrieval and Classification Techniques
- Advanced battery technologies research
- Electric and Hybrid Vehicle Technologies
- Image Processing and 3D Reconstruction
- Financial Markets and Investment Strategies
- Guidance and Control Systems
- Embedded Systems and FPGA Design
- Silicon Carbide Semiconductor Technologies
- Capital Investment and Risk Analysis
- Market Dynamics and Volatility
- Advanced Neural Network Applications
- Wireless Power Transfer Systems
- Age of Information Optimization
Changchun University of Technology
2025
RWTH Aachen University
2023-2024
State Key Laboratory of Remote Sensing Science
2024
Beijing Normal University
2024
Northeast Electric Power University
2023-2024
McMaster University
2021-2024
Chang'an University
2020-2023
Henan University of Technology
2023
University of the Cordilleras
2023
Jülich Aachen Research Alliance
2023
Highly accurate state of charge (SOC) estimation lithium-ion batteries is one the key technologies battery management systems in electric vehicles. The performance SOC directly influences driving range and safety these Due to external disturbances, temperature variation electromagnetic interference, becomes difficult. To accurately estimate batteries, this article presents a novel machine-learning method address risk gradient explosion decent using dynamic nonlinear auto-regressive models...
Lithium-ion batteries have been widely used for energy storage systems and vehicle industries, highly accurate remaining useful life (RUL) prediction of lithium-ion is one the key technologies on prognostics health management. However, uncertainty quantification reliability RUL ignored. To describe avoid over-fitting phenomenon, a model combining Monte Carlo Dropout (MC_dropout) gated recurrent unit (GRU) proposed. Firstly, indirect indicator extracted gray relation analysis (GRA) to analyze...
Accurate state of charge (SOC) estimation lithium-ion batteries is a fundamental prerequisite for ensuring the normal and safe operation electric vehicles, it also key technology component in battery management systems. In recent years, SOC methods based on data-driven approaches have gained significant popularity. However, these commonly face issue poor model generalization limited robustness. To address such issues, this study proposes closed-loop method simulated annealing-optimized...
An accurate state of charge (SOC) estimation depends on an battery model. The influence nonlinear and unstable interference factors makes the SOC difficult. To obtain model, a method based NARX (nonlinear autoregressive network with exogenous inputs) recurrent neural moving window is proposed. This paper improves accuracy, modelling speed robustness from following three aspects. First, to overcome excessive reliance amount data in model training process, used establish external input) delay...
To accurately estimate the state of charge (SOC) aged batteries, capacity estimation must not be ignored. Based on battery charging data, this paper proposes a co-estimation model to SOC and for lithium-ion batteries. First, new health indicator is extracted based data lithium batteries; second, estimated by least squares support vector machine (LSSVM). The results are recorded memory gate used as input estimation. Third, moving window method adopted address long-term dependency loss problem...
Deep learning-based hyperspectral images (HSIs) classification methods have made significant progress recently, catching the attention of academia and industry. However, existing studies HSIs mainly focus on closed-set environment with assumption that ground classes are fixed known, ignoring complexity diversity objects in real world. As a result, unknown will be forced into known classes. To solve this problem, we propose novel spectral-spatial evidential learning network (SSEL) combines an...
During disaster response, it is very important to obtain the information of collapsed building distribution accurately and quickly. However, limited by some practical factors, existed methods often suffer from contradiction between accuracy efficiency damage extraction. This paper proposed a simple effective framework rapid recognize objects using pre-disaster maps post-disaster quasi-panchromatic remote sensing images. The method validated several historical disasters in xBD dataset tested...