The dynamics for multi-link spatial flexible manipulator arms is investigated. The system considered here is an N-flexible-link manipulator driven by N DC-motors through N revolute flexiblejoints. The flexibility of e...The dynamics for multi-link spatial flexible manipulator arms is investigated. The system considered here is an N-flexible-link manipulator driven by N DC-motors through N revolute flexiblejoints. The flexibility of each flexible joint is modeled as a linearly elastic torsional spring, and the mass of the joint is also considered. For the flexibility of the link, all of the stretching deformation, bending deformation and the torsional deformation are included. The complete governing equations of motion of the system are derived via the Lagrange equations. The nonlinear description of the deformation field of the flexible link is adopted in the dynamic modeling, and thus the dynamic stiffening effects are captured. Based on this model, a general-purpose software package for dynamic simulation of multi-link spatial flexible manipulator arms is developed. Several illustrative examples are given to validate the algorithm presented in this paper and to indicate that not only dynamic stiffening effects but also the flexibility of the structure has significant influence on the dynamic performance of the manipulator.展开更多
目前,大部分将知识图谱引入推荐系统的方法只是将已知的表层知识图谱实体进行引入,没有对图谱的内在关系进行预测和挖掘,因此无法利用知识图谱中的隐藏关系。针对上述问题,提出联合学习推荐模型E-TUP(enhance towards understanding of ...目前,大部分将知识图谱引入推荐系统的方法只是将已知的表层知识图谱实体进行引入,没有对图谱的内在关系进行预测和挖掘,因此无法利用知识图谱中的隐藏关系。针对上述问题,提出联合学习推荐模型E-TUP(enhance towards understanding of user preference),使用E-CP(enhance canonical polyadic)进行知识图谱补全并将完整信息进行传递。利用储存空间负采样方法,将优质负例三元组进行存储,并随训练过程进行更新,以提高知识图谱补全中负例三元组的质量。链接预测实验结果显示,储存空间方法使E-TUP模型链接预测准确率对比现有模型最高提升10.3%。在MovieLens-1m和DBbook2014数据集上进行推荐实验,在多个评价指标上取得最佳结果,对比现有模型实现最高5.5%的提升,表明E-TUP可以有效利用知识图谱中的隐藏关系提高模型推荐准确率。基于汽车维修数据进行推荐实验,结果表明E-TUP可以有效推荐相关知识。展开更多
智能反射表面(Intelligent Reflecting Surface,IRS)能够对入射其上的信号进行一定的相位和幅度的变换,从而达到信号的精确传输,提高信号的覆盖和传输效率。但是这种优势都是在已知精确的信道状态信息(Channel State Information,CSI)...智能反射表面(Intelligent Reflecting Surface,IRS)能够对入射其上的信号进行一定的相位和幅度的变换,从而达到信号的精确传输,提高信号的覆盖和传输效率。但是这种优势都是在已知精确的信道状态信息(Channel State Information,CSI)的前提下才能达到。基于IRS元件的无源性,精确的CSI很难得到。针对此问题使用压缩感知(Compressive Sensing,CS)算法结合深度学习(Deep Learning,DL)的方法来解决。使用共链路结构来优化传统的压缩感知算法,能够在更低的导频开销和信噪比(Signal to Noise Ratio,SNR)下获得更好的归一化均方误差(Normalized Mean Square Error,NMSE)。将信道估计问题看作为去噪问题,把优化后的CS算法所得结果看作含有噪声的CSI,使用多重深层降噪块网络对其进一步去噪,得到更加精确的CSI。实验表明,所提算法较对比算法在相同SNR下有更好的精度。展开更多
基金supported by the National Natural Science Foundations of China (10772085,11272155 and 11132007)333 Project of Jiangsu Province,China(BRA2011172)NUST Research Funding,China(2011YBXM32)
文摘The dynamics for multi-link spatial flexible manipulator arms is investigated. The system considered here is an N-flexible-link manipulator driven by N DC-motors through N revolute flexiblejoints. The flexibility of each flexible joint is modeled as a linearly elastic torsional spring, and the mass of the joint is also considered. For the flexibility of the link, all of the stretching deformation, bending deformation and the torsional deformation are included. The complete governing equations of motion of the system are derived via the Lagrange equations. The nonlinear description of the deformation field of the flexible link is adopted in the dynamic modeling, and thus the dynamic stiffening effects are captured. Based on this model, a general-purpose software package for dynamic simulation of multi-link spatial flexible manipulator arms is developed. Several illustrative examples are given to validate the algorithm presented in this paper and to indicate that not only dynamic stiffening effects but also the flexibility of the structure has significant influence on the dynamic performance of the manipulator.
文摘目前,大部分将知识图谱引入推荐系统的方法只是将已知的表层知识图谱实体进行引入,没有对图谱的内在关系进行预测和挖掘,因此无法利用知识图谱中的隐藏关系。针对上述问题,提出联合学习推荐模型E-TUP(enhance towards understanding of user preference),使用E-CP(enhance canonical polyadic)进行知识图谱补全并将完整信息进行传递。利用储存空间负采样方法,将优质负例三元组进行存储,并随训练过程进行更新,以提高知识图谱补全中负例三元组的质量。链接预测实验结果显示,储存空间方法使E-TUP模型链接预测准确率对比现有模型最高提升10.3%。在MovieLens-1m和DBbook2014数据集上进行推荐实验,在多个评价指标上取得最佳结果,对比现有模型实现最高5.5%的提升,表明E-TUP可以有效利用知识图谱中的隐藏关系提高模型推荐准确率。基于汽车维修数据进行推荐实验,结果表明E-TUP可以有效推荐相关知识。
文摘智能反射表面(Intelligent Reflecting Surface,IRS)能够对入射其上的信号进行一定的相位和幅度的变换,从而达到信号的精确传输,提高信号的覆盖和传输效率。但是这种优势都是在已知精确的信道状态信息(Channel State Information,CSI)的前提下才能达到。基于IRS元件的无源性,精确的CSI很难得到。针对此问题使用压缩感知(Compressive Sensing,CS)算法结合深度学习(Deep Learning,DL)的方法来解决。使用共链路结构来优化传统的压缩感知算法,能够在更低的导频开销和信噪比(Signal to Noise Ratio,SNR)下获得更好的归一化均方误差(Normalized Mean Square Error,NMSE)。将信道估计问题看作为去噪问题,把优化后的CS算法所得结果看作含有噪声的CSI,使用多重深层降噪块网络对其进一步去噪,得到更加精确的CSI。实验表明,所提算法较对比算法在相同SNR下有更好的精度。
