Contrary to the aliasing defect between the adjacent intrinsic model functions(IMFs) existing in empirical model decomposition(EMD), a new method of detecting dynamic unbalance with cardan shaft in high-speed train wa...Contrary to the aliasing defect between the adjacent intrinsic model functions(IMFs) existing in empirical model decomposition(EMD), a new method of detecting dynamic unbalance with cardan shaft in high-speed train was proposed by applying the combination between EMD, Hankel matrix, singular value decomposition(SVD) and normalized Hilbert transform(NHT). The vibration signals of gimbal installed base were decomposed through EMD to get different IMFs. The Hankel matrix constructed through the single IMF was orthogonally executed through SVD. The critical singular values were selected to reconstruct vibration signs on the basis of the key stack of singular values. Instantaneous frequencys(IFs) of reconstructed vibration signs were applied to detect dynamic unbalance with shaft and eliminated clutter spectrum caused by the aliasing defect between the adjacent IMFs, which highlighted the failure characteristics. The method was verified by test data in the unbalance condition of dynamic cardan shaft. The results show that the method effectively detects the fault vibration characteristics caused by cardan shaft dynamic unbalance and extracts the nature vibration features. With comparison to the traditional EMD-NHT, clarity and failure characterization force are significantly improved.展开更多
Target echo detection in the presence of strong reverberation is investigated by means of singular value decomposition (SVD) method. Simulation results indicate that the method can efficiently separate the target echo...Target echo detection in the presence of strong reverberation is investigated by means of singular value decomposition (SVD) method. Simulation results indicate that the method can efficiently separate the target echo from the reverberation and can improve the detection of target echo.展开更多
应力强度因子是预测荷载作用下结构中裂纹产生和扩展的重要参数。半解析的比例边界有限元法结合了有限元和边界元法的优势,在裂纹尖端或存在奇异应力的区域不需要局部网格细化,可以直接提取应力强度因子。在比例边界有限元法计算应力强...应力强度因子是预测荷载作用下结构中裂纹产生和扩展的重要参数。半解析的比例边界有限元法结合了有限元和边界元法的优势,在裂纹尖端或存在奇异应力的区域不需要局部网格细化,可以直接提取应力强度因子。在比例边界有限元法计算应力强度因子的框架下,引入随机参数进行蒙特卡罗模拟(Monte Carlo simulation, MCS),并提出一种新颖的基于MCS的不确定量化分析。与直接的MCS不同,采用奇异值分解构造低阶的子空间,降低系统的自由度,并使用径向基函数对子空间进行近似,通过子空间的线性组合获得新的结构响应,实现基于MCS的快速不确定量化分析。考虑不同荷载状况下,结构形状参数和材料属性参数对应力强度因子的影响,使用改进的MCS计算应力强度因子的统计特征,量化不确定参数对结构的影响。最后通过若干算例验证了该算法的准确性和有效性。展开更多
构建大规模茶芽目标检测数据集是一项耗时且繁琐的任务,为了降低数据集构建成本,探索少量标注样本的算法尤为必要。本文提出了YSVD-Tea(YOLO singular value decomposition for tea bud detection)算法,通过将预训练模型中的基础卷积替...构建大规模茶芽目标检测数据集是一项耗时且繁琐的任务,为了降低数据集构建成本,探索少量标注样本的算法尤为必要。本文提出了YSVD-Tea(YOLO singular value decomposition for tea bud detection)算法,通过将预训练模型中的基础卷积替换为3个连续的矩阵结构,实现了对YOLOX算法结构的重构。通过维度变化和奇异值分解操作,将预训练权重转换为与重构算法结构相对应的权重,从而将需要进行迁移学习的权重和需要保留的权重分离开,实现保留预训练模型先验信息的目的。在3种不同数量的数据集上分别进行了训练和验证。在最小数量的1/3数据集上,YSVD-Tea算法相较于改进前的YOLOX算法,mAP提高20.3个百分点。对比测试集与训练集的性能指标,YSVD-Tea算法在测试集与训练集的mAP差距仅为21.9%,明显小于YOLOX的40.6%和Faster R-CNN的55.4%。在数量最大的数据集上,YOLOX算法精确率、召回率、F1值、mAP分别为86.4%、87.0%、86.7%和88.3%,相较于对比算法均最高。YSVD-Tea在保证良好性能的同时,能够更好地适应少量标注样本的茶芽目标检测任务。展开更多
基金Projects(61134002,51305358)supported by the National Natural Science Foundation of ChinaProject(PIL1303)supported by the Open Project of State Key Laboratory of Precision Measurement Technology and Instruments,ChinaProject(2682014BR032)supported by the Fundamental Research Funds for the Central Universities,China
文摘Contrary to the aliasing defect between the adjacent intrinsic model functions(IMFs) existing in empirical model decomposition(EMD), a new method of detecting dynamic unbalance with cardan shaft in high-speed train was proposed by applying the combination between EMD, Hankel matrix, singular value decomposition(SVD) and normalized Hilbert transform(NHT). The vibration signals of gimbal installed base were decomposed through EMD to get different IMFs. The Hankel matrix constructed through the single IMF was orthogonally executed through SVD. The critical singular values were selected to reconstruct vibration signs on the basis of the key stack of singular values. Instantaneous frequencys(IFs) of reconstructed vibration signs were applied to detect dynamic unbalance with shaft and eliminated clutter spectrum caused by the aliasing defect between the adjacent IMFs, which highlighted the failure characteristics. The method was verified by test data in the unbalance condition of dynamic cardan shaft. The results show that the method effectively detects the fault vibration characteristics caused by cardan shaft dynamic unbalance and extracts the nature vibration features. With comparison to the traditional EMD-NHT, clarity and failure characterization force are significantly improved.
文摘Target echo detection in the presence of strong reverberation is investigated by means of singular value decomposition (SVD) method. Simulation results indicate that the method can efficiently separate the target echo from the reverberation and can improve the detection of target echo.
文摘应力强度因子是预测荷载作用下结构中裂纹产生和扩展的重要参数。半解析的比例边界有限元法结合了有限元和边界元法的优势,在裂纹尖端或存在奇异应力的区域不需要局部网格细化,可以直接提取应力强度因子。在比例边界有限元法计算应力强度因子的框架下,引入随机参数进行蒙特卡罗模拟(Monte Carlo simulation, MCS),并提出一种新颖的基于MCS的不确定量化分析。与直接的MCS不同,采用奇异值分解构造低阶的子空间,降低系统的自由度,并使用径向基函数对子空间进行近似,通过子空间的线性组合获得新的结构响应,实现基于MCS的快速不确定量化分析。考虑不同荷载状况下,结构形状参数和材料属性参数对应力强度因子的影响,使用改进的MCS计算应力强度因子的统计特征,量化不确定参数对结构的影响。最后通过若干算例验证了该算法的准确性和有效性。
文摘构建大规模茶芽目标检测数据集是一项耗时且繁琐的任务,为了降低数据集构建成本,探索少量标注样本的算法尤为必要。本文提出了YSVD-Tea(YOLO singular value decomposition for tea bud detection)算法,通过将预训练模型中的基础卷积替换为3个连续的矩阵结构,实现了对YOLOX算法结构的重构。通过维度变化和奇异值分解操作,将预训练权重转换为与重构算法结构相对应的权重,从而将需要进行迁移学习的权重和需要保留的权重分离开,实现保留预训练模型先验信息的目的。在3种不同数量的数据集上分别进行了训练和验证。在最小数量的1/3数据集上,YSVD-Tea算法相较于改进前的YOLOX算法,mAP提高20.3个百分点。对比测试集与训练集的性能指标,YSVD-Tea算法在测试集与训练集的mAP差距仅为21.9%,明显小于YOLOX的40.6%和Faster R-CNN的55.4%。在数量最大的数据集上,YOLOX算法精确率、召回率、F1值、mAP分别为86.4%、87.0%、86.7%和88.3%,相较于对比算法均最高。YSVD-Tea在保证良好性能的同时,能够更好地适应少量标注样本的茶芽目标检测任务。
