With the recent advancements in machine learning technology, the accuracy of autonomous driving object detection models has significantly improved. However, due to the complexity and variability of real-world traffic scenarios, such as extreme weather conditions, unconventional lighting, and unknown traffic participants, there is inherent uncertainty in autonomous driving object detection models, which may affect the planning and control in autonomous driving. Thus, the rapid and accurate quantification of this uncertainty is crucial. It contributes to a better understanding of the intentions of autonomous vehicles and strengthens trust in autonomous driving technology. This research pioneers in quantifying uncertainty in the YOLOv5 object detection model, thereby improving the accuracy and speed of probabilistic object detection, and addressing the real-time operational constraints of current models in autonomous driving contexts. Specifically, a novel probabilistic object detection model named M-YOLOv5 is proposed, which employs the MC-drop method to capture discrepancies between detection results and the real world. These discrepancies are then converted into Gaussian parameters for class scores and predicted bounding box coordinates to quantify uncertainty. Moreover, due to the limitations of the Mean Average Precision (MAP) evaluation metric, we introduce a new measure, Probability-based Detection Quality (PDQ), which is incorporated as a component of the loss function. This metric simultaneously assesses the quality of label uncertainty and positional uncertainty. Experiments demonstrate that compared to the original YOLOv5 algorithm, the M-YOLOv5 algorithm shows a 74.7% improvement in PDQ. When compared with the most advanced probabilistic object detection models targeting the MS COCO dataset, M-YOLOv5 achieves a 14% increase in MAP, a 17% increase in PDQ, and a 65% improvement in FPS. Furthermore, against the state-of-the-art probabilistic object detection models for the BDD100K dataset, M-YOLOv5 exhibits a 31.67% enhancement in MAP and a 125.6% increase in FPS.

As the energy density of lithium-ion batteries continues to increase, battery safety issues characterized by thermal runaway have become increasingly severe. Battery safety issues have severely restricted the large-scale application of power batteries. Among them, the flammable liquid organic electrolyte is one of the main reasons for the safety hazards of battery thermal runaway. This article reviews the flame-retardant mechanism and research progress of phosphorus-based flame-retardant additives, nitrogen-based flame-retardant additives, and halogen-based flame-retardant additives. The design strategies of conventional flame-retardant additives and intelligent flame-retardant additives in lithium-ion batteries are summarized. Finally, a development direction and research prospects of flame-retardant additives in lithium-ion battery electrolytes are prospected.

Gas diffusion layers (GDLs) are the most rigid layers in a 5‐layer or 7‐layer membrane electrode assembly (MEA) of a proton exchange membrane fuel cell. Therefore, in the fuel cell analysis, the mechanical properties of GDLs have a great impact on the stress distribution of the membrane as well as the performance of the whole cell. However, the mechanical properties of GDLs are not sufficiently studied. Nonlinear behavior of GDLs under cyclic compression is discussed rarely in literature. The existing model takes both constraints into consideration, but due to a geometrical oversimplification of the carbon paper microstructure, it shows some deviation, which cannot be overcome by selecting appropriate parameters. In this paper, the geometry of carbon paper microstructure has been reanalyzed. Based on the improved geometry formula, a modified model of carbon paper GDL is presented and verified by experimental data. Furthermore, both the experimental mechanical characteristics are achieved as support data for the improved model.

As a solution of high efficiency and clean energy, fuel cell technologies, especially proton exchange membrane fuel cell (PEMFC), have caught extensive attention. However, after decades of development, the performances of PEMFCs are far from achieving the target from the Department of Energy (DOE). Thus, further understanding of the degradation mechanism is needed to overcome this obstacle. Due to the importance of proton exchange membrane in a PEMFC, the degradation of the membrane, such as hygrothermal aging effect on its properties, are particularly necessary. In this work, a thick membrane (Nafion N117), which is always used as an ionic polymer for the PEMFCs, has been analyzed. Experimental investigation is performed for understanding the mechanical endurance of the bare membranes under different loading conditions. Tensile tests are conducted to compare the mechanical property evolution of two kinds of bare-membrane specimens including the dog-bone and the deeply double edge notched (DDEN) types. Both dog-bone and DDEN specimens were subjected to a series of degradation tests with different cycling times and wide humidity ranges. The tensile tests are repeated for both kinds of specimens to assess the strain-stress relations. Furthermore, Fourier transform infrared spectroscopy (FT-IR), X-ray diffraction (XRD) and Scanning electron microscope (SEM) observation and water absorption measurement were conducted to speculate the cause of this variation. The initial cracks along with the increasing of bound water content were speculated as the primary cause.