The state of in situ stress is a crucial parameter in subsurface engineering,especially for critical projects like nuclear waste repository.As one of the two ISRM suggested methods,the overcoring(OC)method is widely u...The state of in situ stress is a crucial parameter in subsurface engineering,especially for critical projects like nuclear waste repository.As one of the two ISRM suggested methods,the overcoring(OC)method is widely used to estimate the full stress tensors in rocks by independent regression analysis of the data from each OC test.However,such customary independent analysis of individual OC tests,known as no pooling,is liable to yield unreliable test-specific stress estimates due to various uncertainty sources involved in the OC method.To address this problem,a practical and no-cost solution is considered by incorporating into OC data analysis additional information implied within adjacent OC tests,which are usually available in OC measurement campaigns.Hence,this paper presents a Bayesian partial pooling(hierarchical)model for combined analysis of adjacent OC tests.We performed five case studies using OC test data made at a nuclear waste repository research site of Sweden.The results demonstrate that partial pooling of adjacent OC tests indeed allows borrowing of information across adjacent tests,and yields improved stress tensor estimates with reduced uncertainties simultaneously for all individual tests than they are independently analysed as no pooling,particularly for those unreliable no pooling stress estimates.A further model comparison shows that the partial pooling model also gives better predictive performance,and thus confirms that the information borrowed across adjacent OC tests is relevant and effective.展开更多
The qualitative analysis on the behavior of partial penetrated weld pool transferring from pulsed peak current to base current in pulsed TIG welding is carried out in this paper. Based on the analysis results, the mat...The qualitative analysis on the behavior of partial penetrated weld pool transferring from pulsed peak current to base current in pulsed TIG welding is carried out in this paper. Based on the analysis results, the mathematical models for 3D liquid surface shape of partial penetrated weld pool in pulsed TIG welding are created including surface potential energy model, gravitational energy model and volumetric potential energy. The numerical simulation with these models and the experiments on low carbon steel are carried out using the software Surface Evolver. The simulation results and model are then amended with experimental results. Two important characteristic quantities, the liquid metal coverage ratio and the stripping width of liquid metal, are put forward in this paper, which paves a way for further weld pool full penetration control.展开更多
For an analysis of the oxidation behavior of UO2 nuclear fuel pellet under a loss of water coolant accident in a spent nuclear fuel pool of an LWR, thermodynamic assessments of UO2 oxidation were carried out under var...For an analysis of the oxidation behavior of UO2 nuclear fuel pellet under a loss of water coolant accident in a spent nuclear fuel pool of an LWR, thermodynamic assessments of UO2 oxidation were carried out under various atmospheric conditions. In a steam atmosphere, it was assessed that UO2 would not be fully oxidized into U3O8 due to the relatively lower oxygen partial pressure, while UO2 will be fully oxidized into U3O8 in an air atmosphere. In an air and steam mixture atmosphere, the UO2 oxidation was dominantly affected by the air volumetric fraction, because of the relatively higher oxygen partial pressure of air. In addition, the effect of H2 volumetric fraction on the oxygen partial pressure under a mixture atmosphere was calculated, and it was revealed that UO2 pellet oxidation could be reduced above the critical value of H2 volumetric fraction.展开更多
图池化作为图神经网络中重要的组件,在获取图的多粒度信息的过程中扮演了重要角色。而当前的图池化操作均以平等地位看待数据点,普遍未考虑利用邻域内数据之间的偏序关系,从而造成图结构信息破坏。针对此问题,本文提出一种基于偏序关系...图池化作为图神经网络中重要的组件,在获取图的多粒度信息的过程中扮演了重要角色。而当前的图池化操作均以平等地位看待数据点,普遍未考虑利用邻域内数据之间的偏序关系,从而造成图结构信息破坏。针对此问题,本文提出一种基于偏序关系的多视图多粒度图表示学习框架(multi-view and multi-granularity graph representation learning based on partial order relationships,MVMGr-PO),它通过从节点特征视图、图结构视图以及全局视图对节点进行综合评分,进而基于节点之间的偏序关系进行下采样操作。相比于其他图表示学习方法,MVMGr-PO可以有效地提取多粒度图结构信息,从而可以更全面地表征图的内在结构和属性。此外,MVMGr-PO可以集成多种图神经网络架构,包括GCN(graph convolutional network)、GAT(graph attention network)以及GraphSAGE(graph sample and aggregate)等。通过在6个数据集上进行实验评估,与现有基线模型相比,MVMGr-PO在分类准确率上有明显提升。展开更多
随着电子设备的广泛应用,印刷电路板(Printed Circuit Board,PCB)在电子制造行业中具有重要意义.然而,由于制造过程中的不完美和环境因素的干扰,PCB上可能存在微小的缺陷.因此,开发高效准确的缺陷检测算法对于确保产品质量至关重要.针对...随着电子设备的广泛应用,印刷电路板(Printed Circuit Board,PCB)在电子制造行业中具有重要意义.然而,由于制造过程中的不完美和环境因素的干扰,PCB上可能存在微小的缺陷.因此,开发高效准确的缺陷检测算法对于确保产品质量至关重要.针对PCB微小缺陷检测问题,本文提出了一种基于多维注意力机制的高精度PCB微小缺陷检测算法.为降低网络的模型参数量和计算量,引入部分卷积(Partial Convolution,PConv),将ELAN(Efficient Layer Aggregation Network)模块设计为更加高效的P-ELAN,同时,为增强网络对微小缺陷的特征提取能力,引入多维注意力机制(Multi-Dimensional Attention Mechanism,MDAM)的全维动态卷积(Omni-dimensional Dynamic Convolution,ODConv)并结合部分卷积,设计了POD-CSP(Partial ODconv-Cross Stage Partial)和POD-MP(Partial ODconv-Max Pooling)跨阶段部分网络模块,提出了OD-Neck结构.最后,本文基于(Youo Only Look Once version 7,YOLOv7)提出了对小目标更加高效的YOLO-POD模型,并在训练阶段采用一种新颖的Alpha-SIoU损失函数对网络进行优化.实验结果表明,YOLO-POD的检测精确率和召回率分别达到了98.31%和97.09%,并在多个指标上取得了领先优势,尤其是对于更严格的(mean Average Precision at IoU threshold of 0.75,mAP75)指标,比原始的YOLOv7模型提高28%.验证了YOLO-POD在PCB缺陷检测性能中具有较高的准确性和鲁棒性,满足高精度的检测要求,可为PCB制造行业提供有效的检测解决方案.展开更多
目的随着自动驾驶和辅助驾驶的快速发展,交通标志识别研究变得越来越重要。但是现阶段交通标志识别算法对交通标志识别的精度较低,尤其在面对目标背景较为复杂、光照不足和小目标交通标志的场景时,更加容易出现错检和漏检情况。针对以...目的随着自动驾驶和辅助驾驶的快速发展,交通标志识别研究变得越来越重要。但是现阶段交通标志识别算法对交通标志识别的精度较低,尤其在面对目标背景较为复杂、光照不足和小目标交通标志的场景时,更加容易出现错检和漏检情况。针对以上问题,提出了一种改进YOLOv7(you only look once version 7)的交通标志识别模型。方法首先,采用空间金字塔池化快速跨级部分连接(spatial pyramid pooling fast cross stage partial concat,SPPFCSPC)方法,替换YOLOv7算法使用的空间金字塔池化跨级部分连接(spatial pyramid pooling cross stage partial concat,SPPCSPC)方法,提高算法的特征提取能力。其次,采用加权双向特征金字塔网络(bi-directional feature pyra⁃mid network,BiFPN),增强算法的多尺度特征融合能力。接着,采用一种新的框间距离度量的归一化Wasserstein距离(normalized Wasserstein distance,NWD)方法,解决传统的IoU(intersection over union)度量对小目标交通标志检测过于敏感的问题。最后,使用特征内容的感知重组(content-aware reassembly of feature,CARAFE)算子,通过输入的特征,自适应生成上采样内核,有效地增加模型的感受域,更好地利用目标周边的信息,减少交通标志错检和漏检情况。结果实验结果表明,在减少算法参数量的基础上,改进算法在TT100K交通标志数据集上的mAP@0.5和mAP@0.5∶0.9值分别达到了92.50%和72.21%,较原始的YOLOv7算法分别提高了3.24%和1.83%。同时,在具有小目标特性的CCTSDB交通标志数据集和整理的国外交通标志数据集上验证了模型改进的有效性。结论通过实验验证和主客观评价,证明了本文改进算法的可行性,能够有效地对多种环境下的小目标交通标志进行识别,并在降低算法参数量的前提下,进一步提高了YOLOv7算法对交通标志识别的平均精度。展开更多
基金supported by the Guangdong Basic and Applied Basic Research Foundation(2023A1515011244).
文摘The state of in situ stress is a crucial parameter in subsurface engineering,especially for critical projects like nuclear waste repository.As one of the two ISRM suggested methods,the overcoring(OC)method is widely used to estimate the full stress tensors in rocks by independent regression analysis of the data from each OC test.However,such customary independent analysis of individual OC tests,known as no pooling,is liable to yield unreliable test-specific stress estimates due to various uncertainty sources involved in the OC method.To address this problem,a practical and no-cost solution is considered by incorporating into OC data analysis additional information implied within adjacent OC tests,which are usually available in OC measurement campaigns.Hence,this paper presents a Bayesian partial pooling(hierarchical)model for combined analysis of adjacent OC tests.We performed five case studies using OC test data made at a nuclear waste repository research site of Sweden.The results demonstrate that partial pooling of adjacent OC tests indeed allows borrowing of information across adjacent tests,and yields improved stress tensor estimates with reduced uncertainties simultaneously for all individual tests than they are independently analysed as no pooling,particularly for those unreliable no pooling stress estimates.A further model comparison shows that the partial pooling model also gives better predictive performance,and thus confirms that the information borrowed across adjacent OC tests is relevant and effective.
文摘The qualitative analysis on the behavior of partial penetrated weld pool transferring from pulsed peak current to base current in pulsed TIG welding is carried out in this paper. Based on the analysis results, the mathematical models for 3D liquid surface shape of partial penetrated weld pool in pulsed TIG welding are created including surface potential energy model, gravitational energy model and volumetric potential energy. The numerical simulation with these models and the experiments on low carbon steel are carried out using the software Surface Evolver. The simulation results and model are then amended with experimental results. Two important characteristic quantities, the liquid metal coverage ratio and the stripping width of liquid metal, are put forward in this paper, which paves a way for further weld pool full penetration control.
文摘For an analysis of the oxidation behavior of UO2 nuclear fuel pellet under a loss of water coolant accident in a spent nuclear fuel pool of an LWR, thermodynamic assessments of UO2 oxidation were carried out under various atmospheric conditions. In a steam atmosphere, it was assessed that UO2 would not be fully oxidized into U3O8 due to the relatively lower oxygen partial pressure, while UO2 will be fully oxidized into U3O8 in an air atmosphere. In an air and steam mixture atmosphere, the UO2 oxidation was dominantly affected by the air volumetric fraction, because of the relatively higher oxygen partial pressure of air. In addition, the effect of H2 volumetric fraction on the oxygen partial pressure under a mixture atmosphere was calculated, and it was revealed that UO2 pellet oxidation could be reduced above the critical value of H2 volumetric fraction.
文摘图池化作为图神经网络中重要的组件,在获取图的多粒度信息的过程中扮演了重要角色。而当前的图池化操作均以平等地位看待数据点,普遍未考虑利用邻域内数据之间的偏序关系,从而造成图结构信息破坏。针对此问题,本文提出一种基于偏序关系的多视图多粒度图表示学习框架(multi-view and multi-granularity graph representation learning based on partial order relationships,MVMGr-PO),它通过从节点特征视图、图结构视图以及全局视图对节点进行综合评分,进而基于节点之间的偏序关系进行下采样操作。相比于其他图表示学习方法,MVMGr-PO可以有效地提取多粒度图结构信息,从而可以更全面地表征图的内在结构和属性。此外,MVMGr-PO可以集成多种图神经网络架构,包括GCN(graph convolutional network)、GAT(graph attention network)以及GraphSAGE(graph sample and aggregate)等。通过在6个数据集上进行实验评估,与现有基线模型相比,MVMGr-PO在分类准确率上有明显提升。
文摘随着电子设备的广泛应用,印刷电路板(Printed Circuit Board,PCB)在电子制造行业中具有重要意义.然而,由于制造过程中的不完美和环境因素的干扰,PCB上可能存在微小的缺陷.因此,开发高效准确的缺陷检测算法对于确保产品质量至关重要.针对PCB微小缺陷检测问题,本文提出了一种基于多维注意力机制的高精度PCB微小缺陷检测算法.为降低网络的模型参数量和计算量,引入部分卷积(Partial Convolution,PConv),将ELAN(Efficient Layer Aggregation Network)模块设计为更加高效的P-ELAN,同时,为增强网络对微小缺陷的特征提取能力,引入多维注意力机制(Multi-Dimensional Attention Mechanism,MDAM)的全维动态卷积(Omni-dimensional Dynamic Convolution,ODConv)并结合部分卷积,设计了POD-CSP(Partial ODconv-Cross Stage Partial)和POD-MP(Partial ODconv-Max Pooling)跨阶段部分网络模块,提出了OD-Neck结构.最后,本文基于(Youo Only Look Once version 7,YOLOv7)提出了对小目标更加高效的YOLO-POD模型,并在训练阶段采用一种新颖的Alpha-SIoU损失函数对网络进行优化.实验结果表明,YOLO-POD的检测精确率和召回率分别达到了98.31%和97.09%,并在多个指标上取得了领先优势,尤其是对于更严格的(mean Average Precision at IoU threshold of 0.75,mAP75)指标,比原始的YOLOv7模型提高28%.验证了YOLO-POD在PCB缺陷检测性能中具有较高的准确性和鲁棒性,满足高精度的检测要求,可为PCB制造行业提供有效的检测解决方案.
文摘目的随着自动驾驶和辅助驾驶的快速发展,交通标志识别研究变得越来越重要。但是现阶段交通标志识别算法对交通标志识别的精度较低,尤其在面对目标背景较为复杂、光照不足和小目标交通标志的场景时,更加容易出现错检和漏检情况。针对以上问题,提出了一种改进YOLOv7(you only look once version 7)的交通标志识别模型。方法首先,采用空间金字塔池化快速跨级部分连接(spatial pyramid pooling fast cross stage partial concat,SPPFCSPC)方法,替换YOLOv7算法使用的空间金字塔池化跨级部分连接(spatial pyramid pooling cross stage partial concat,SPPCSPC)方法,提高算法的特征提取能力。其次,采用加权双向特征金字塔网络(bi-directional feature pyra⁃mid network,BiFPN),增强算法的多尺度特征融合能力。接着,采用一种新的框间距离度量的归一化Wasserstein距离(normalized Wasserstein distance,NWD)方法,解决传统的IoU(intersection over union)度量对小目标交通标志检测过于敏感的问题。最后,使用特征内容的感知重组(content-aware reassembly of feature,CARAFE)算子,通过输入的特征,自适应生成上采样内核,有效地增加模型的感受域,更好地利用目标周边的信息,减少交通标志错检和漏检情况。结果实验结果表明,在减少算法参数量的基础上,改进算法在TT100K交通标志数据集上的mAP@0.5和mAP@0.5∶0.9值分别达到了92.50%和72.21%,较原始的YOLOv7算法分别提高了3.24%和1.83%。同时,在具有小目标特性的CCTSDB交通标志数据集和整理的国外交通标志数据集上验证了模型改进的有效性。结论通过实验验证和主客观评价,证明了本文改进算法的可行性,能够有效地对多种环境下的小目标交通标志进行识别,并在降低算法参数量的前提下,进一步提高了YOLOv7算法对交通标志识别的平均精度。
