The rapid expansion of the electric vehicle (EV) market has raised significant safety concerns, particularly regarding fires caused by the thermal runaway of lithium-ion batteries. To address this issue, this study investigates the real-time fire detection performance of segmentation-based object detection models for EVs. The evaluated models include YOLOv5-Seg, YOLOv8-Seg, YOLOv11-Seg, Mask R-CNN, and Cascade Mask R-CNN. Performance is analyzed using metrics such as precision, recall, F1-score, mAP50, and FPS. The experimental results reveal that the YOLO-based models outperform Mask R-CNN and Cascade Mask R-CNN across all evaluation metrics. In particular, YOLOv11-Seg demonstrates superior accuracy in delineating fire and smoke boundaries, achieving minimal false positives and high reliability under diverse fire scenarios. Additionally, its real-time processing speed of 136.99 FPS validates its capability for rapid detection and response, even in complex fire environments. Conversely, Mask R-CNN and Cascade Mask R-CNN exhibit suboptimal performance in terms of precision, recall, and FPS, limiting their applicability to real-time fire detection systems. This study establishes YOLO-based segmentation models, particularly the advanced YOLOv11-Seg, as highly effective EV fire detection and response systems.
5 November 2024 in IEEE Transactions on Industrial Electronics
A power factor correction (PFC) converter is essential for a switching mode power supply (SMPS), which is used in light-emitting diode televisions to comply with the harmonic current standard of IEC 61000-3-2 Class D. However, because of the high inductor peak current of a boost PFC converter, large-sized inductors and output electrolytic capacitors are employed. Consequently, the power density of the SMPS decreases, while the associated cost increases. This article presents a novel control method to minimize the inductor peak current in the widely used boost critical conduction mode PFC converters. The proposed scheme employs constant on-time control to satisfy the harmonic standard as well as peak current mode control to reduce the inductor current, thereby shaping the inductor current into a trapezoidal form. Thus, the proposed method reduces the size of the inductor and output electrolytic capacitors while satisfying the harmonic standards. The detailed analysis and comprehensive design procedures for the proposed method are presented. The effectiveness of the proposed approach has been verified using a 300W prototype.