When simulating or designing plate heat exchangers for multicomponent mixtures, most designers are often perplexed with the question on how to choose or estimate the physical property param- eters and hope to have a r...When simulating or designing plate heat exchangers for multicomponent mixtures, most designers are often perplexed with the question on how to choose or estimate the physical property param- eters and hope to have a reliable database that could be adopted. The commercial codes HYSYS supply the physical property package on over 1500 pure substances and over 16 000 binary coefficients for them. This work has briefly presented an efficient communication interface based on the Microsoft Component Object Model （COM） between inner plate heat exchanger simulation codes and the HYSYS package. The application of a custom-made HYSYS-COM interface has shown high efficiency, such as significant reduction of time needed for evaluating each process stream＇s properties. This automation method can be conveniently extended to further optimization study for any specific operation device such as heat transfers, columns, and other facilities.展开更多
Multi-license plate detection in complex scenes is still a challenging task because of multiple vehicle license plates with different sizes and classes in the images having complex background.The edge features of high...Multi-license plate detection in complex scenes is still a challenging task because of multiple vehicle license plates with different sizes and classes in the images having complex background.The edge features of high-density distribution and the high curvature features of stroke turning of Chinese character are important signs to distinguish Chinese license plate from other objects.To accurately detect multiple vehicle license plates with different sizes and classes in complex scenes,a multi-object detection of Chinese license plate method based on improved YOLOv3 network was proposed in this research.The improvements include replacing the residual block of the YOLOv3 backbone network with the Inception-ResNet-A block,imbedding the SPP block into the detection network,cutting the redundant Inception-ResNet-A block to suit for the multi-license plate detection task,and clustering the ground truth boxes of license plates to obtain a new set of anchor boxes.A Chinese vehicle license plate image dataset was built for training and testing the improved network,and the location and class of the license plates in each image were accurately labeled.The dataset has 62,153 pieces of images and 4 classes of China vehicle license plates,almost images have multiple license plates with different sizes.Experiments demonstrated that the multilicense plate detection method obtained 83.4%mAP,98.88%precision,98.17%recall,98.52 F1 score,89.196 BFLOPS and 22 FPS on the test dataset,and whole performance was better than the other five compared networks including YOLOv3,SSD,Faster-RCNN,EfficientDet and RetinaNet.展开更多
传统中文车牌识别方法对场景约束有要求,算法实时性差,且无法被部署在边缘设备上。针对上述问题,文中提出一种基于YOLO(You Only Look Once)的无约束场景中文车牌检测与识别方法。该方法分为车牌检测和车牌字符识别两个模块。在车牌检...传统中文车牌识别方法对场景约束有要求,算法实时性差,且无法被部署在边缘设备上。针对上述问题,文中提出一种基于YOLO(You Only Look Once)的无约束场景中文车牌检测与识别方法。该方法分为车牌检测和车牌字符识别两个模块。在车牌检测部分,使用改进的YOLOv5模型,在预测目标候选区域的基础上多预测4组关键点用于车牌矫正,并使用在COCO数据集上训练的预训练模型进行训练,减少了由环境复杂引起的误检问题,具有高实时性。在车牌字符识别部分,改进了CRNN(Convolutional Recurrent Neural Network)模型,减少了算法的参数量和计算量,使其能成功部署于各类边缘设备。实验结果表明所提出的车牌识别方法能在复杂环境中高效检测并识别车牌。文中提出的车牌检测模型在车牌检测数据集上的map值相较Retina-face提升了3.0%,车牌字符识别模型在车牌识别数据集上精确度相比LPR-Net提升了4.2%。展开更多
大气辐射传输会引起卫星传感器获取的信息与实际信息存在出入,进而导致彩钢板建筑信息提取的不准确。据此,文章以兰州市安宁区为例,利用地物光谱仪和卫星影像获取典型彩钢板光谱数据,确定彩钢板反射率影响因素,结合影响因素测试彩钢板...大气辐射传输会引起卫星传感器获取的信息与实际信息存在出入,进而导致彩钢板建筑信息提取的不准确。据此,文章以兰州市安宁区为例,利用地物光谱仪和卫星影像获取典型彩钢板光谱数据,确定彩钢板反射率影响因素,结合影响因素测试彩钢板反射率并分析光谱特征。然后将实测光谱数据分别与影像经FLAASH(Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes)模型和6S(Second Simulation of the Satellite Signal in the Solar Spectrum)模型大气校正后的光谱信息进行光谱匹配,以确定适合不同颜色彩钢板光谱数据的大气校正方法。结果表明,彩钢板光谱反射率曲线均能反映彩钢板表面颜色特性;FLAASH大气校正更能反映蓝、红彩钢板建筑的真实反射率;6S模型大气校正更能反映白色彩钢板建筑的真实反射率。本研究将为后续彩钢板建筑信息自动解译提供技术支持。展开更多
基金the National High Technology Research and Development Program of China(863 Program)(2006AA05Z216)the DUT Youth Fond
文摘When simulating or designing plate heat exchangers for multicomponent mixtures, most designers are often perplexed with the question on how to choose or estimate the physical property param- eters and hope to have a reliable database that could be adopted. The commercial codes HYSYS supply the physical property package on over 1500 pure substances and over 16 000 binary coefficients for them. This work has briefly presented an efficient communication interface based on the Microsoft Component Object Model （COM） between inner plate heat exchanger simulation codes and the HYSYS package. The application of a custom-made HYSYS-COM interface has shown high efficiency, such as significant reduction of time needed for evaluating each process stream＇s properties. This automation method can be conveniently extended to further optimization study for any specific operation device such as heat transfers, columns, and other facilities.
基金supported by the China Sichuan Science and Technology Program under Grant 2019YFG0299the Fundamental Research Funds of China West Normal University under Grant 19B045the Research Foundation for Talents of China Normal University under Grant 17YC163。
文摘Multi-license plate detection in complex scenes is still a challenging task because of multiple vehicle license plates with different sizes and classes in the images having complex background.The edge features of high-density distribution and the high curvature features of stroke turning of Chinese character are important signs to distinguish Chinese license plate from other objects.To accurately detect multiple vehicle license plates with different sizes and classes in complex scenes,a multi-object detection of Chinese license plate method based on improved YOLOv3 network was proposed in this research.The improvements include replacing the residual block of the YOLOv3 backbone network with the Inception-ResNet-A block,imbedding the SPP block into the detection network,cutting the redundant Inception-ResNet-A block to suit for the multi-license plate detection task,and clustering the ground truth boxes of license plates to obtain a new set of anchor boxes.A Chinese vehicle license plate image dataset was built for training and testing the improved network,and the location and class of the license plates in each image were accurately labeled.The dataset has 62,153 pieces of images and 4 classes of China vehicle license plates,almost images have multiple license plates with different sizes.Experiments demonstrated that the multilicense plate detection method obtained 83.4%mAP,98.88%precision,98.17%recall,98.52 F1 score,89.196 BFLOPS and 22 FPS on the test dataset,and whole performance was better than the other five compared networks including YOLOv3,SSD,Faster-RCNN,EfficientDet and RetinaNet.
文摘大气辐射传输会引起卫星传感器获取的信息与实际信息存在出入,进而导致彩钢板建筑信息提取的不准确。据此,文章以兰州市安宁区为例,利用地物光谱仪和卫星影像获取典型彩钢板光谱数据,确定彩钢板反射率影响因素,结合影响因素测试彩钢板反射率并分析光谱特征。然后将实测光谱数据分别与影像经FLAASH(Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes)模型和6S(Second Simulation of the Satellite Signal in the Solar Spectrum)模型大气校正后的光谱信息进行光谱匹配,以确定适合不同颜色彩钢板光谱数据的大气校正方法。结果表明,彩钢板光谱反射率曲线均能反映彩钢板表面颜色特性;FLAASH大气校正更能反映蓝、红彩钢板建筑的真实反射率;6S模型大气校正更能反映白色彩钢板建筑的真实反射率。本研究将为后续彩钢板建筑信息自动解译提供技术支持。
