切段式机收甘蔗含杂率的自动测量可以客观评估机收甘蔗到糖厂入榨前的质量。针对现有抽样称重估算杂质方式效率低且主观性强的问题,以及因田间环境较为复杂使得检测目标蔗段存在运动状态变换导致的模糊、光照强度变化和蔗叶遮挡等技术难...切段式机收甘蔗含杂率的自动测量可以客观评估机收甘蔗到糖厂入榨前的质量。针对现有抽样称重估算杂质方式效率低且主观性强的问题,以及因田间环境较为复杂使得检测目标蔗段存在运动状态变换导致的模糊、光照强度变化和蔗叶遮挡等技术难点,提出了一种基于改进YOLOv5安装在切段式甘蔗机上的机收蔗含杂率检测的方法。首先,针对工业相机拍摄的蔗段目标为小目标的应用场景,增加小目标检测层,增强网络模型对其的专注;其次,将C3模块替换成C2f模块,提高网络模型对小物体、低对比度目标的检测速度和检测精度;最后,加入加权交并比WIoU(Weighted Intersection over Union)损失函数,提升预测框的回归精度,增强数据集训练效果。试验结果表明:基于改进YOLOv5的机收蔗含杂率检测模型,蔗段识别准确率达95.2%、mAP(mean Average Precision)值为62.5%,相较于原始YOLOv5模型分别提高了15.3、13.5个百分点,性能优于YOLOv7、YOLOv8等模型。在台架试验中,改进后模型检测的含杂率平均相对误差为19.58%,比改进前模型降低了38.12个百分点;含杂率平均值为7.31%,比人工测量的实际含杂率高出0.05个百分点。因此,此方法是一种实时性强、效率高、准确性高且能全量检测机收蔗含杂率的方法,能够为田间甘蔗收获作业质量提供技术支撑。展开更多
KIT-5/Beta composite supports were synthesized using an in situ self-assembly hydrothermal method,and NiW/KIT-5/Beta catalysts were prepared by impregnation.A series of characterization techniques were utilized to eva...KIT-5/Beta composite supports were synthesized using an in situ self-assembly hydrothermal method,and NiW/KIT-5/Beta catalysts were prepared by impregnation.A series of characterization techniques were utilized to evaluate the influence of varying hydrothermal synthesis temperatures on the physicochemical properties of both the KIT-5/Beta supports and the resulting catalysts.The catalytic performances of catalysts were evaluated under reaction conditions of 320℃,4 MPa H_(2)pressure,and a weight hourly space velocity(WHSV)of 4.8 h^(-1)for hydrodenitrogenation(HDN)of quinoline.The results indicated that the specific surface area and pore structure of the materials could be effectively regulated by adjusting the hydrothermal synthesis temperature,which in turn influenced the number of active sites on the catalyst.The NiW/KB-125 catalyst,synthesized at 125℃,presented the highest quinoline HDN efficiency(96.8%),which can be attributed to its favorable pore channel structure,greater Brønsted acid number,higher degree of metal sulfidation(80.12%)and appropriate metal-support interaction(MSI).展开更多
文摘切段式机收甘蔗含杂率的自动测量可以客观评估机收甘蔗到糖厂入榨前的质量。针对现有抽样称重估算杂质方式效率低且主观性强的问题,以及因田间环境较为复杂使得检测目标蔗段存在运动状态变换导致的模糊、光照强度变化和蔗叶遮挡等技术难点,提出了一种基于改进YOLOv5安装在切段式甘蔗机上的机收蔗含杂率检测的方法。首先,针对工业相机拍摄的蔗段目标为小目标的应用场景,增加小目标检测层,增强网络模型对其的专注;其次,将C3模块替换成C2f模块,提高网络模型对小物体、低对比度目标的检测速度和检测精度;最后,加入加权交并比WIoU(Weighted Intersection over Union)损失函数,提升预测框的回归精度,增强数据集训练效果。试验结果表明:基于改进YOLOv5的机收蔗含杂率检测模型,蔗段识别准确率达95.2%、mAP(mean Average Precision)值为62.5%,相较于原始YOLOv5模型分别提高了15.3、13.5个百分点,性能优于YOLOv7、YOLOv8等模型。在台架试验中,改进后模型检测的含杂率平均相对误差为19.58%,比改进前模型降低了38.12个百分点;含杂率平均值为7.31%,比人工测量的实际含杂率高出0.05个百分点。因此,此方法是一种实时性强、效率高、准确性高且能全量检测机收蔗含杂率的方法,能够为田间甘蔗收获作业质量提供技术支撑。
基金Supported by the Autonomous Research Project of SKLCC(2024BWZ003)Strategic Priority Research Program of the Chinese Academy of Sciences(XDA0390401)the Doctoral Research Start-up Funding of Shanxi Institute of Technology(026012).
文摘KIT-5/Beta composite supports were synthesized using an in situ self-assembly hydrothermal method,and NiW/KIT-5/Beta catalysts were prepared by impregnation.A series of characterization techniques were utilized to evaluate the influence of varying hydrothermal synthesis temperatures on the physicochemical properties of both the KIT-5/Beta supports and the resulting catalysts.The catalytic performances of catalysts were evaluated under reaction conditions of 320℃,4 MPa H_(2)pressure,and a weight hourly space velocity(WHSV)of 4.8 h^(-1)for hydrodenitrogenation(HDN)of quinoline.The results indicated that the specific surface area and pore structure of the materials could be effectively regulated by adjusting the hydrothermal synthesis temperature,which in turn influenced the number of active sites on the catalyst.The NiW/KB-125 catalyst,synthesized at 125℃,presented the highest quinoline HDN efficiency(96.8%),which can be attributed to its favorable pore channel structure,greater Brønsted acid number,higher degree of metal sulfidation(80.12%)and appropriate metal-support interaction(MSI).
