In this paper, we applied the rough sets to the point cluster and river network selection. In order to meet the requirements of rough sets, first, we structuralize and quantify the spatial information of objects by co...In this paper, we applied the rough sets to the point cluster and river network selection. In order to meet the requirements of rough sets, first, we structuralize and quantify the spatial information of objects by convex hull, triangulated irregular network (TIN), Voronoi diagram, etc.;second, we manually assign decisional attributes to the information table according to conditional attributes. In doing so, the spatial information and attribute information are integrated together to evaluate the importance of points and rivers by rough sets theory. Finally, we select the point cluster and the river network in a progressive manner. The experimental results show that our method is valid and effective. In comparison with previous work, our method has the advantage to adaptively consider the spatial and attribute information at the same time without any a priori knowledge.展开更多
Reduced order models(ROMs) based on the snapshots on the CFD high-fidelity simulations have been paid great attention recently due to their capability of capturing the features of the complex geometries and flow confi...Reduced order models(ROMs) based on the snapshots on the CFD high-fidelity simulations have been paid great attention recently due to their capability of capturing the features of the complex geometries and flow configurations. To improve the efficiency and precision of the ROMs, it is indispensable to add extra sampling points to the initial snapshots, since the number of sampling points to achieve an adequately accurate ROM is generally unknown in prior, but a large number of initial sampling points reduces the parsimony of the ROMs. A fuzzy-clustering-based adding-point strategy is proposed and the fuzzy clustering acts an indicator of the region in which the precision of ROMs is relatively low. The proposed method is applied to construct the ROMs for the benchmark mathematical examples and a numerical example of hypersonic aerothermodynamics prediction for a typical control surface. The proposed method can achieve a 34.5% improvement on the efficiency than the estimated mean squared error prediction algorithm and shows same-level prediction accuracy.展开更多
Modal analysis,which provides modal parameters including frequencies,damping ratios,and mode shapes,is essential for assessing structural safety in structural health monitoring.Automated operational modal analysis(AOM...Modal analysis,which provides modal parameters including frequencies,damping ratios,and mode shapes,is essential for assessing structural safety in structural health monitoring.Automated operational modal analysis(AOMA)offers a promising alternative to traditional methods that depend heavily on human intervention and engineering judgment.However,estimating structural dynamic properties and managing spurious modes remain challenging due to uncertainties in practical application conditions.To address this issue,we propose an automated modal identification approach comprising three key aspects:(1)identification of modal parameters using covariance-driven stochastic subspace identification;(2)automated interpretation of the stabilization diagram;(3)an improved self-adaptive algorithm for grouping physical modes based on ordering points to identify the clustering structure(OPTICS)combined with k-nearest neighbors(KNN).The proposed approach can play a crucial role in enabling real-time structural health monitoring without human intervention.A simulated 10-story shear frame was used to verify the methodology.Identification results from a cable-stayed bridge demonstrate the practicality of the proposed method for conducting AOMA in engineering practice.The proposed approach can automatically identify modal parameters with high accuracy,making it suitable for a real-time structural health monitoring framework.展开更多
针对大跨径钢结构桥梁高强螺栓群松动病害人工巡检效率低、风险大及智能化检测中数据集样本不足、检测精度不高、泛化性较弱等问题,提出一种基于深度学习的钢结构桥梁高强螺栓群松动病害识别方法。首先利用基于深度学习的YOLOv10(You On...针对大跨径钢结构桥梁高强螺栓群松动病害人工巡检效率低、风险大及智能化检测中数据集样本不足、检测精度不高、泛化性较弱等问题,提出一种基于深度学习的钢结构桥梁高强螺栓群松动病害识别方法。首先利用基于深度学习的YOLOv10(You Only Look Once version 10)目标检测算法对螺栓进行目标检测;其次采用匈牙利(Kuhn-Munkres)算法对高强螺栓群基准图和待检测图进行二分匹配,同时将图片划分为单螺栓子图;然后提出一种多任务学习注意力机制的高强螺栓关键点检测算法,设计空间聚类的螺栓六角点后处理模块,融合透视变换,自上而下检测螺栓6个角点;最后对比基准图与待检测图螺栓关键点的变化,计算螺栓松动角度。采用该方法对复杂环境下的室内、室外钢桁梁节段模型及实桥钢桁梁上的高强螺栓群进行检测试验。结果表明:该方法能准确检测出螺栓是否松动,检测准确率达到了97%以上,召回率均达到了95%以上,该方法具有较好的实用价值和工程前景。展开更多
An empirical dynamic model of burn-through point（BTP）in sintering process was developed.The K-means clustering was used to feed distribution according to the cold bed permeability,which was estimated by the superfic...An empirical dynamic model of burn-through point（BTP）in sintering process was developed.The K-means clustering was used to feed distribution according to the cold bed permeability,which was estimated by the superficial gas velocity in the cold stage.For each clustering,a novel genetic programming（NGP）was proposed to construct the empirical model of the waste gas temperature and the bed pressure drop in the sintering stage.The least square method（LSM）and M-estimator were adopted in NGP to improve the ability to compute and resist disturbance.Simulation results show the superiority of the proposed method.展开更多
The relationship between fractal point pattern modeling and statistical methods of pa- rameter estimation in point-process modeling is reviewed. Statistical estimation of the cluster fractal dimension by using Ripley...The relationship between fractal point pattern modeling and statistical methods of pa- rameter estimation in point-process modeling is reviewed. Statistical estimation of the cluster fractal dimension by using Ripley＇s K-function has advantages in comparison with the more commonly used methods of box-counting and cluster fractal dimension estimation because it corrects for edge effects, not only for rectangular study areas but also for study areas with curved boundaries determined by re- gional geology. Application of box-counting to estimate the fractal dimension of point patterns has the disadvantage that, in general, it is subject to relatively strong ＂roll-off＂ effects for smaller boxes. Point patterns used for example in this paper are mainly for gold deposits in the Abitibi volcanic belt on the Canadian Shield. Additionally, it is proposed that, worldwide, the local point patterns of podiform Cr, volcanogenic massive sulphide and porphyry copper deposits, which are spatially distributed within irregularly shaped favorable tracts, satisfy the fractal clustering model with similar fractal dimensions. The problem of deposit size （metal tonnage） is also considered. Several examples are provided of cases in which the Pareto distribution provides good results for the largest deposits in metal size-frequency distribution modeling.展开更多
为减少因船舶偏离航道而造成的搁浅、碰撞航标或桥墩等水上交通事故,提出了一种基于多目相机自动识别航道的桥区航行异常船舶预警方法。基于YOLOv5(You Only Look Once version 5)目标检测算法,联动变、定焦相机识别并定位航标和船舶,...为减少因船舶偏离航道而造成的搁浅、碰撞航标或桥墩等水上交通事故,提出了一种基于多目相机自动识别航道的桥区航行异常船舶预警方法。基于YOLOv5(You Only Look Once version 5)目标检测算法,联动变、定焦相机识别并定位航标和船舶,跟踪并记录船舶航迹点,计算船舶的速度和航向并推算船位。提出了一种基于视频船舶航迹点的密度聚类识别航道两侧航标的方法,实现航道自适应可视化。基于船位推算识别并预警航行状态异常的船舶。实验结果表明:航标、船舶的检测正确率分别达84.8%、90.3%,相较单一相机检测模型,正确率分别提高了32.1%、5.5%;能够自适应可视化航道并识别、预警航行异常船舶。展开更多
While considerable progress has been achieved in radiation influence on the solid states, the quantitative assessment of defect production is very scarce. In this paper radiation defects studies in silicon crystals ar...While considerable progress has been achieved in radiation influence on the solid states, the quantitative assessment of defect production is very scarce. In this paper radiation defects studies in silicon crystals are briefly reviewed and comprehensively analyzed depending on irradiation energy and dose, paying special attention to electron irradiation in wide energy spectrum when crystal lattice disordered regions (clusters) occur. Electron irradiation, which is a simple way to introduce intrinsic defects, was used as one of the most powerful techniques to study point and cluster defects which affect properties of semiconductors depending on irradiation energy. Fundamental aspects of radiation induced defects are discussed and it is shown that they bring information on the threshold energy for atomic displacement, on the recombination of vacancy—interstitial pair and mainly, on radiation defects cluster formation which essentially influences on the irradiating material properties. The determination of the irradiation critical dose and energy for the formation of homogeneous disordered regions (clusters) are detailed.展开更多
文摘In this paper, we applied the rough sets to the point cluster and river network selection. In order to meet the requirements of rough sets, first, we structuralize and quantify the spatial information of objects by convex hull, triangulated irregular network (TIN), Voronoi diagram, etc.;second, we manually assign decisional attributes to the information table according to conditional attributes. In doing so, the spatial information and attribute information are integrated together to evaluate the importance of points and rivers by rough sets theory. Finally, we select the point cluster and the river network in a progressive manner. The experimental results show that our method is valid and effective. In comparison with previous work, our method has the advantage to adaptively consider the spatial and attribute information at the same time without any a priori knowledge.
基金Supported by National Natural Science Foundation of China(Grant No.11372036)
文摘Reduced order models(ROMs) based on the snapshots on the CFD high-fidelity simulations have been paid great attention recently due to their capability of capturing the features of the complex geometries and flow configurations. To improve the efficiency and precision of the ROMs, it is indispensable to add extra sampling points to the initial snapshots, since the number of sampling points to achieve an adequately accurate ROM is generally unknown in prior, but a large number of initial sampling points reduces the parsimony of the ROMs. A fuzzy-clustering-based adding-point strategy is proposed and the fuzzy clustering acts an indicator of the region in which the precision of ROMs is relatively low. The proposed method is applied to construct the ROMs for the benchmark mathematical examples and a numerical example of hypersonic aerothermodynamics prediction for a typical control surface. The proposed method can achieve a 34.5% improvement on the efficiency than the estimated mean squared error prediction algorithm and shows same-level prediction accuracy.
基金supported by the National Natural Science Foundation of China(No.52408200)the Natural Science Foundation of Jiangsu Province(No.BK20240996)+1 种基金China,the Suzhou Science and Technology Plan(Basic Research)Project(No.SJC2023002)China,and the Natural Science Research Projects of Colleges and Universities in Jiangsu Province(No.24KJB560022),China.
文摘Modal analysis,which provides modal parameters including frequencies,damping ratios,and mode shapes,is essential for assessing structural safety in structural health monitoring.Automated operational modal analysis(AOMA)offers a promising alternative to traditional methods that depend heavily on human intervention and engineering judgment.However,estimating structural dynamic properties and managing spurious modes remain challenging due to uncertainties in practical application conditions.To address this issue,we propose an automated modal identification approach comprising three key aspects:(1)identification of modal parameters using covariance-driven stochastic subspace identification;(2)automated interpretation of the stabilization diagram;(3)an improved self-adaptive algorithm for grouping physical modes based on ordering points to identify the clustering structure(OPTICS)combined with k-nearest neighbors(KNN).The proposed approach can play a crucial role in enabling real-time structural health monitoring without human intervention.A simulated 10-story shear frame was used to verify the methodology.Identification results from a cable-stayed bridge demonstrate the practicality of the proposed method for conducting AOMA in engineering practice.The proposed approach can automatically identify modal parameters with high accuracy,making it suitable for a real-time structural health monitoring framework.
文摘针对大跨径钢结构桥梁高强螺栓群松动病害人工巡检效率低、风险大及智能化检测中数据集样本不足、检测精度不高、泛化性较弱等问题,提出一种基于深度学习的钢结构桥梁高强螺栓群松动病害识别方法。首先利用基于深度学习的YOLOv10(You Only Look Once version 10)目标检测算法对螺栓进行目标检测;其次采用匈牙利(Kuhn-Munkres)算法对高强螺栓群基准图和待检测图进行二分匹配,同时将图片划分为单螺栓子图;然后提出一种多任务学习注意力机制的高强螺栓关键点检测算法,设计空间聚类的螺栓六角点后处理模块,融合透视变换,自上而下检测螺栓6个角点;最后对比基准图与待检测图螺栓关键点的变化,计算螺栓松动角度。采用该方法对复杂环境下的室内、室外钢桁梁节段模型及实桥钢桁梁上的高强螺栓群进行检测试验。结果表明:该方法能准确检测出螺栓是否松动,检测准确率达到了97%以上,召回率均达到了95%以上,该方法具有较好的实用价值和工程前景。
基金Sponsored by National Natural Science Foundation of China(60736021,21076179)National High-Technologies Research and Development Program of China(863 Program)(2006AA04Z184,2007AA041406)+1 种基金Key Technologies Research and Development Program of Zhejiang Province of China(2006C11066,2006C31051)Natural Science Foundation of Zhejiang Province of China(Y4080339)
文摘An empirical dynamic model of burn-through point（BTP）in sintering process was developed.The K-means clustering was used to feed distribution according to the cold bed permeability,which was estimated by the superficial gas velocity in the cold stage.For each clustering,a novel genetic programming（NGP）was proposed to construct the empirical model of the waste gas temperature and the bed pressure drop in the sintering stage.The least square method（LSM）and M-estimator were adopted in NGP to improve the ability to compute and resist disturbance.Simulation results show the superiority of the proposed method.
基金supported by Geological Survey of Canada and China University of Geosciences (Wuhan)
文摘The relationship between fractal point pattern modeling and statistical methods of pa- rameter estimation in point-process modeling is reviewed. Statistical estimation of the cluster fractal dimension by using Ripley＇s K-function has advantages in comparison with the more commonly used methods of box-counting and cluster fractal dimension estimation because it corrects for edge effects, not only for rectangular study areas but also for study areas with curved boundaries determined by re- gional geology. Application of box-counting to estimate the fractal dimension of point patterns has the disadvantage that, in general, it is subject to relatively strong ＂roll-off＂ effects for smaller boxes. Point patterns used for example in this paper are mainly for gold deposits in the Abitibi volcanic belt on the Canadian Shield. Additionally, it is proposed that, worldwide, the local point patterns of podiform Cr, volcanogenic massive sulphide and porphyry copper deposits, which are spatially distributed within irregularly shaped favorable tracts, satisfy the fractal clustering model with similar fractal dimensions. The problem of deposit size （metal tonnage） is also considered. Several examples are provided of cases in which the Pareto distribution provides good results for the largest deposits in metal size-frequency distribution modeling.
文摘为减少因船舶偏离航道而造成的搁浅、碰撞航标或桥墩等水上交通事故,提出了一种基于多目相机自动识别航道的桥区航行异常船舶预警方法。基于YOLOv5(You Only Look Once version 5)目标检测算法,联动变、定焦相机识别并定位航标和船舶,跟踪并记录船舶航迹点,计算船舶的速度和航向并推算船位。提出了一种基于视频船舶航迹点的密度聚类识别航道两侧航标的方法,实现航道自适应可视化。基于船位推算识别并预警航行状态异常的船舶。实验结果表明:航标、船舶的检测正确率分别达84.8%、90.3%,相较单一相机检测模型,正确率分别提高了32.1%、5.5%;能够自适应可视化航道并识别、预警航行异常船舶。
文摘While considerable progress has been achieved in radiation influence on the solid states, the quantitative assessment of defect production is very scarce. In this paper radiation defects studies in silicon crystals are briefly reviewed and comprehensively analyzed depending on irradiation energy and dose, paying special attention to electron irradiation in wide energy spectrum when crystal lattice disordered regions (clusters) occur. Electron irradiation, which is a simple way to introduce intrinsic defects, was used as one of the most powerful techniques to study point and cluster defects which affect properties of semiconductors depending on irradiation energy. Fundamental aspects of radiation induced defects are discussed and it is shown that they bring information on the threshold energy for atomic displacement, on the recombination of vacancy—interstitial pair and mainly, on radiation defects cluster formation which essentially influences on the irradiating material properties. The determination of the irradiation critical dose and energy for the formation of homogeneous disordered regions (clusters) are detailed.
