eTransportation, Journal Year: 2024, Volume and Issue: unknown, P. 100391 - 100391
Published: Dec. 1, 2024
Language: Английский
Energy storage materials, Journal Year: 2025, Volume and Issue: unknown, P. 104051 - 104051
Published: Feb. 1, 2025
Language: Английский
Citations
1
Nature Communications, Journal Year: 2025, Volume and Issue: 16(1)
Published: March 22, 2025
Energy management technologies have significant potential to optimize electric vehicle performance and support global energy sustainability. However, despite extensive research, their real-world application remains limited due reliance on simulations, which often fail bridge the gap between theory practice. This study introduces a data-driven framework based offline reinforcement learning. By leveraging operation data, proposed approach eliminates need for manually designed rules or high-fidelity simulations. It integrates seamlessly into existing frameworks, enhancing after deployment. The method is tested fuel cell vehicles, optimizing consumption reducing system degradation. Real-world data from an monitoring in China validate its effectiveness. results demonstrate that consistently achieves superior under diverse conditions. Notably, with increasing availability, improves significantly, 88% 98.6% of theoretical optimum two updates. Training over 60 million kilometers enables learning agent generalize across previously unseen corner-case scenarios. These findings highlight methods enhance efficiency longevity through large-scale utilization. vehicles rely manual design limiting application. Here, authors introduce optimizes degradation using historical achieving improved adaptability.
Language: Английский
Citations
1
Published: Feb. 4, 2025
Energy storage and management technologies are key in the deployment operation of electric vehicles (EVs). To keep up with continuous innovations energy technologies, it is necessary to develop corresponding strategies. In this Review, we discuss technological advances management. strategies, such as lifetime prognostics fault detection, can reduce EV charging times while enhancing battery safety. Combining advanced sensor data prediction algorithms improve efficiency EVs, increasing their driving range, encouraging uptake technology. also facilitates clean like vehicle-to-grid storage, recycling for grid renewable electricity. We offer an overview technical challenges solve trends better EVs. Electric require careful batteries systems increase range operating safely. This Review describes techniques used both hybrid considers future options vehicles.
Language: Английский
Citations
0
Annals of the University of Craiova Electrical Engineering Series, Journal Year: 2025, Volume and Issue: 48, P. 55 - 60
Published: Jan. 23, 2025
This paper presents the importance of finding suitable configurations for Artificial Intelligence and Machine Learning algorithms correct data preprocessing a waveform problem. In area, this step is one most important it influences performance result model. The experiments different were done using National Instruments Automated (NI AutoML), web application created everyone that allows us to easily change model by just clicking some buttons. work shows how influenced modifying what columns use, splitting or adding deleting steps in pipeline. All results obtained are analyzed paper. proposed flow generic enough be applied all use cases. To exemplify whole process, synthetic set generating current voltage an RL circuit was chosen part created. represent two waveforms: they recorded during test time. end process each has label associated: Pass Fail. classification problem defined help improving fail detection rate.
Language: Английский
Citations
0
Journal of Energy Chemistry, Journal Year: 2025, Volume and Issue: unknown
Published: March 1, 2025
Language: Английский
Citations
0
eTransportation, Journal Year: 2025, Volume and Issue: unknown, P. 100420 - 100420
Published: April 1, 2025
Language: Английский
Citations
0
eTransportation, Journal Year: 2025, Volume and Issue: unknown, P. 100426 - 100426
Published: April 1, 2025
Language: Английский
Citations
0
eTransportation, Journal Year: 2025, Volume and Issue: unknown, P. 100425 - 100425
Published: April 1, 2025
Language: Английский
Citations
0
Advanced Materials Technologies, Journal Year: 2025, Volume and Issue: unknown
Published: May 3, 2025
Abstract Deformation of lithium batteries is known as a hazardous problem possibly leading to fire or fuming, while deformation sensors are not attached the batteries. The comes from complex phenomena inside batteries, resulting in difficult estimation. To display battery deterioration status more easily, CSDS (colorimetric stress‐detectable separator) presented that separator sensor made structural color polymer, enabling mechanical stress with colors. polymer consists aligned silica nanoparticles and PEGPEA (Poly (ethylene glycol) phenyl ether acrylate) acrylic displaying specific wavelength depending on particle gaps. observe color, an observation window opened electrode battery. showed there two stages for gas expansion by change green (≈540 nm) red (≈580 nm). also displayed blue near edge hole, growing crystals. Those results will contribute improvement safety easy check outside packs.
Language: Английский
Citations
0
eTransportation, Journal Year: 2024, Volume and Issue: unknown, P. 100370 - 100370
Published: Oct. 1, 2024
Language: Английский
Citations
2