A5009469146- Advanced Battery Technologies Research
- Advancements in Battery Materials
- Electric Vehicles and Infrastructure
- Electric and Hybrid Vehicle Technologies
- Reliability and Maintenance Optimization
- Advanced Battery Materials and Technologies
- Anomaly Detection Techniques and Applications
- Traffic Prediction and Management Techniques
- Stability and Control of Uncertain Systems
- Vehicle emissions and performance
- Sentiment Analysis and Opinion Mining
- Healthcare Technology and Patient Monitoring
- Cardiac Arrest and Resuscitation
- Distributed Control Multi-Agent Systems
- Neural Networks Stability and Synchronization
- Fault Detection and Control Systems
- Cloud Computing and Resource Management
- Software-Defined Networks and 5G
- Internet Traffic Analysis and Secure E-voting
- Food Supply Chain Traceability
- Gas Sensing Nanomaterials and Sensors
- Consumer Retail Behavior Studies
- Text and Document Classification Technologies
- Autonomous Vehicle Technology and Safety
- Phytoplasmas and Hemiptera pathogens
Nanjing University of Posts and Telecommunications
2024
Beijing Institute of Technology
2017-2024
South China Agricultural University
2024
Nanjing University of Aeronautics and Astronautics
2020-2021
Northeastern University
2016-2020
Hangzhou Dianzi University
2018-2020
Hebei University
2020
University of Shanghai for Science and Technology
2016-2018
State Key Laboratory of Automotive Simulation and Control
2018
State of health is a critical state which evaluates the degradation level batteries. However, it cannot be measured directly but requires estimation. While accurate estimation has progressed markedly, time- and resource-consuming experiments to generate target battery labels hinder development methods. In this article, we design deep-learning framework enable in absence labels. This integrates swarm deep neural networks equipped with domain adaptation produce We employ 65 commercial...
Abstract Lithium-ion batteries have always been a focus of research on new energy vehicles, however, their internal reactions are complex, and problems such as battery aging safety not fully understood. In view the preliminary application digital twin in complex systems aerospace, we will opportunity to use solve bottleneck current research. Firstly, this paper arranges development history, basic concepts key technologies twin, summarizes methods challenges modeling, state estimation,...
Sentiment analysis of e-commerce reviews is the hot topic in product quality management, from which manufacturers are able to learn public sentiment about products being sold on websites. Meanwhile, customers can know other people's attitudes same products. This paper proposes deep learning model Bert-BiGRU-Softmax with hybrid masking, review extraction and attention mechanism, applies Bert as input layer extract multi-dimensional feature reviews, Bidirectional GRU hidden obtain semantic...
Abstract With the wide deployment of rechargeable batteries, battery degradation prediction has emerged as a challenging issue. However, life defined by capacity loss provides limited information regarding degradation. In this article, we explore voltage‐capacity curves over lifetime based on sequence to (seq2seq) model. We demonstrate that data one present curve can be used input seq2seq model accurately predict at 100, 200, and 300 cycles ahead. This offers an opportunity update management...
Online estimation of the state power (SoP) lithium-ion batteries is crucial for both battery management system and energy in electric vehicles. In this paper, approach online estimating SoP investigated with a concern impact imprecise charge (SoC). First, characteristics lithium under different health (SoH) conditions are experimented based on typical vehicle driving cycle; then SOP algorithm using genetic (GA) proposed to deal long time-scale application, top that, sensitivity coefficient...
In order to pre-warning the product quality risk of e-commerce platform, this paper studies machine learning algorithm for products assessment, which propose Fuzzy C-Means clustering feature extraction and Cost Sensitive Leaning (CSL)-Naive Bayesia n construct assessment model E-commerce form massive unbalanced data. The experimental results show that Machine Learning based on Spark has better scalability superiority in large-scale data environment, can accurately identify risk.
Driving cycle is essential for the investigation of power management in electrified vehicles. Building a representative driving remains challenge due to complex conditions. In this paper, principal component analysis (PCA) and k-means cluster are employed develop with case Shenyang, China. First all, many road conditions collected, which made up series data including time instantaneous velocity. Then, PCA applied extract main components overall condition K-means used select kinematic...
The performance of lithium-ion batteries will inevitably degrade during the high frequently charging/discharging load applied in electric vehicles. For hybrid vehicles, battery aging not only declines and reliability itself, but it also affects whole energy efficiency vehicle since engine has to participate more. Therefore, management strategy is required be adjusted entire lifespan maintain optimality economy. In this study, tests performances under thirteen different stages are involved a...
This paper focuses on an important research problem of cyberspace security. As active defense technology, intrusion detection plays role in the field network Traditional technologies have problems such as low accuracy, efficiency, and time consuming. The shallow structure machine learning has been unable to respond time. To solve these problems, deep learning-based method studied improve detection. advantage is that it a strong ability for features can handle very complex data. Therefore, we...