YOLSO: You Only Look Small Object

Small object detection is challenging and far from satisfactory. Most general object detectors suffer from two critical issues with small objects: (1) Feature extractor based on classification network cannot express the characteristics of small objects reasonably due to insufficient appearance information of targets and a large amount of background interference around them. (2) The detector requires a much higher location accuracy for small objects than for general objects. This paper proposes an effective and efficient small object detector YOLSO to address the above problems. For feature representation, we analyze the drawbacks in previous backbones and present a Half-Space Shortcut(HSSC) module to build a background-aware backbone. Furthermore, a coarse-to-fine Feature Pyramid Enhancement(FPE) module is introduced for layer-wise aggregation at a granular level to enhance the semantic discriminability. For loss function, we propose an exponential L1 loss to promote the convergence of regression, and a focal IOU loss to focus on prime samples with high classification confidence and high IOU. Both of them significantly improves the location accuracy of small objects. The proposed YOLSO sets state-of-the-art results on two typical small object datasets, MOCOD and VeDAI, at a speed of over 200 FPS. In the meantime, it also outperforms the baseline YOLOv3 by a wide margin on the common COCO dataset.     

Structure-dependent activity and stability of Al2O3 supported Rh catalysts for the steam reforming of n-dodecane

Steam reforming of liquid hydrocarbon fuels is an appealing way for the production of hydrogen. In this work, the Rh/Al₂O₃ catalysts with nanorod (NR), nanofiber (NF) and sponge-shaped (SP) alumina supports were successfully designed for the steam reforming of n-dodecane as a surrogate compound for diesel/jet fuels. The catalysts before and after reaction were well characterized by using ICP, XRD, N₂ adsorption, TEM, HAADF-STEM, H₂-TPR, CO chemisorption, NH₃-TPD, CO₂-TPD, XPS, Al²⁷ NMR and TG. The results confirmed that the dispersion and surface structure of Rh species is quite dependent on the enclosed various morphologies. Rh/Al₂O₃-NR possesses highly dispersed, uniform and accessible Rh particles with the highest percentage of surface electron deficient Rh⁰ active species, which due to the unique properties of Al₂O₃ nanorod including high crystallinity, relatively large alumina particle size, thermal stability, and large pore volume and size. As a consequent, Rh/Al₂O₃-NR catalyst exhibited superior catalytic activity towards steam reforming reactions and hydrogen production rate over other two catalysts. Especially, Rh/Al₂O₃-NR catalyst showed the highest hydrogen production rate of 87,600 mmol g_fuel^?1 g_Rh^?1min^?1 among any Rh-based catalysts and other noble metal-based catalysts to date. After long-term reaction, a significant deactivation occurred on Rh/Al₂O₃–NF and Rh/Al₂O₃-SP catalysts, due to aggregation and sintering of Rh metal particles, coke deposition and poor hydrothermal stability of nanofibrous structure. In contrast, the Rh/Al₂O₃-NR catalyst shows excellent reforming stability with negligible coke formation. No significantly sintering and aggregation of the Rh particles is observed after long-term reaction. Such great catalyst stability can be explained by the role of hydrothermal stable nanorod alumina support, which not only provides a unique environment for the stabilization of uniform and small-size Rh particles but also affords strong surface basic sites.     

Digital twin-based analysis of volumetric error mapping procedures

The evaluation of the volumetric accuracy of a machine tool is an open challenge in the industry, and a wide variety of technical solutions are available in the market and at research level. All solutions have advantages and disadvantages concerning which errors can be measured, the achievable uncertainty, the ease of implementation, possibility of machine integration and automation, the equipment cost and the machine occupation time, and it is not always straightforward which option to choose for each application. The need to ensure accuracy during the whole lifetime of the machine and the availability of monitoring systems developed following the Industry 4.0 trend are pushing the development of measurement systems that can be integrated in the machine to perform semi-automatic verification procedures that can be performed frequently by the machine user to monitor the condition of the machine. Calibrated artefact based calibration and verification solutions have an advantage in this field over laser based solutions in terms of cost and feasibility of machine integration, but they need to be optimized for each machine and customer requirements to achieve the required calibration uncertainty and minimize machine occupation time.This paper introduces a digital twin-based methodology to simulate all relevant effects in an artefact-based machine tool calibration procedure, from the machine itself with its expected error ranges, to the artefact geometry and uncertainty, artefact positions in the workspace, probe uncertainty, compensation model, etc. By parameterizing all relevant variables in the design of the calibration procedure, this simulation methodology can be used to analyse the effect of each design variable on the error mapping uncertainty, which is of great help in adapting the procedure to each specific machine and user requirements. The simulation methodology and the analysis possibilities are illustrated by applying it on a 3-axis milling machine tool.     

Balancing control of a unicycle robot with double gyroscopes using adaptive fuzzy controller

This paper presents a unicycle robot which utilizes the precession effect of a double-gyroscope for lateral balancing and designs an adaptive fuzzy controller to realize the balance control according to its dynamic model. The double gyroscope structure of the unicycle robot can eliminate the pitch angle interference caused by the precession effect and improve the robot's lateral anti-interference ability. An adaptive fuzzy controller is designed based on the dynamic equations of the unicycle robot to improve its robustness. The adaptive controller part improves the anti-interference ability of the unicycle robot, and the fuzzy controller part is used as decoupling controller to reduce the interference of coupling. Simulation and experimental results to verify the anti-interference ability and decoupling effect of the designed controller.     

Effect of wind condition on unintended hydrogen release in a hydrogen refueling station

Ambient condition, especially the wind condition, is an important factor to determine the behavior of hydrogen diffusion during hydrogen release. However, only few studies aim at the quantitative study of the hydrogen diffusion in a wind-exist condition. And very little researches aiming at the variable wind condition have been done. In this paper, the hydrogen diffusion in different wind condition which including the constant wind velocity and the variable wind velocity is investigated numerically. When considering the variable wind velocity, the UDF (user defined function) is compiled. Characteristics of the FGC (flammable gas cloud) and the HMF (hydrogen mass fraction) are analyzed in different wind condition and comparisons are made with the no-wind condition. Results indicate that the constant wind velocity and the variable wind velocity have totally different effect for the determination of hydrogen diffusion. Comparisons between the constant wind velocity and the variable wind velocity indicate that the variable wind velocity may cause a more dangerous situation since there has a larger FGC volume. More importantly, the wind condition has a non-negligible effect when considering the HMF along the radial direction. As the wind velocity increases, the distribution of the HMF along the radial direction is not Gaussian anymore when the distance between the release hole and the observation line exceeds to a critical value. This work can be a supplement of the research on the hydrogen release and diffusion and a valuable reference for the researchers.     

Effect of cooking temperature on texture and flavour binding of braised sauce porcine skin

To investigate the effect of cooking temperature (55, 65, 75, 85 and 95 °C) on texture and flavour binding of braised sauce porcine skin (BSPS), sensory acceptance, microstructure and flavour-binding capacity were investigated during the processing of BSPS. Samples cooked at 85 and 95 °C showed better texture and aroma scores. Hardness and chewiness of BSPS were obviously improved at 85 and 95 °C than control group. Collagen structure was significantly destroyed over 85 °C. The porcine skin collagen heated at 85 and 95 °C showed relatively higher flavour-binding capacity than other samples. The improvement of texture of BSPS was mainly attributed to the degradation of collagen. Higher aroma scores of BSPS were related to intense binding abilities with aroma compounds at 85 and 95 °C. Cooking at 85 or 95 °C could be an optimal cooking temperature for BSPS.     

Porous agarose/Gd-hydroxyapatite composite bone fillers with promoted osteogenesis and antibacterial activity

Artificial bone fillers are essentially required for repairing bone defects, and developing the fillers with synergistic biocompatibility and anti-bacterial activity persists as one of the critical challenges. In this work, a new agarose/gadolinium-doped hydroxyapatite filler with three-dimensional porous structures was fabricated. For the composite filler, agarose provides three-dimensional skeleton and endows porosity, workability, and high specific surface area, hydroxyapatite (HA) offers the biocompatibility, and the rare earth element gadolinium (Gd) acts as the antibacterial agent. X-ray photoelectron spectroscopy detection showed the doping of Gd in HA lattice with the formation of Gd-HA interstitial solid solution. Attenuated total reflection Fourier transform infrared spectroscopy imaging suggested chemical interactions between agarose and Gd-HA, and the physical structure of agarose was tuned by the Gd-doped HA. Cytotoxicity testing and alizarin red staining experiments using mouse pro-osteoblasts (MC3T3-E1) revealed remarkable bioactivity and osteogenic properties of the composite fillers, and proliferation and growth rates of the cells increased in proportion to Gd content in the composites. Antibacterial testing using the gram-positive bacteria S. aureus and the gram-negative bacteria E. coli indicated promising antibacterial properties of the fillers. Meanwhile, the antibacterial properties of composite filles were enhanced with the increase of Gd content. The antibacterial fillers with porous structure and excellent physicomechanical properties show inspiring potential for bone defect repair.     

The influence of FeNi nanoparticles on the microstructures and soft magnetic properties of FeSi soft magnetic composites

In this work, a new type of FeSi/FeNi soft magnetic powder core (SMPC) was successfully fabricated by coating FeNi nanoparticles on the surface of FeSi micrometer powder. The effects of different contents of FeNi nanoparticles on the micromorphology, internal structures, and soft magnetic properties of SMPCs were studied. The results show that FeNi nanoparticles adhere to the surface of FeSi powder, which can effectively fill the air gap between FeSi powder and is beneficial to the compaction of the powder cores during the pressing process. Thus, the density of the SMPCs is increased. Compared to FeSi SMPCs, the comprehensive soft magnetic properties of FeSi/FeNi SMPCs have been greatly improved. When adding 15 wt% FeNi nanoparticles, the SMPCs exhibit excellent magnetic properties with high effective permeability (increased by 43.8 %) and low core loss (decreased by 22.1 %). The high performance FeSi/FeNi SMPCs prepared in this work are expected to be widely used in power choke coils, uninterruptible power supplies, and boosts and inverter inductors.