When the Airborne Early Warning(AEW) radar transmits medial or high Pulse Repetitive Frequency(PRF) signal,the range ambiguity occurs.The clutter of short-range clutter has serious range dependence problem for non-Sid...When the Airborne Early Warning(AEW) radar transmits medial or high Pulse Repetitive Frequency(PRF) signal,the range ambiguity occurs.The clutter of short-range clutter has serious range dependence problem for non-Side Looking Airborne Radar(non-SLAR).As a result,the clutter plus noise covariance matrix can not be estimated correctly,and the performance of clutter suppression obtained by Space-Time Adaptive Processing(STAP) degrades greatly.The uniform linear array has not elevation degrees;therefore,the short-range clutter can not be suppressed directly.A short-range clutter suppression method is proposed.The method first estimate the elevation angles of the ambiguous short-range gate,then eliminates short-range clutter by space time interpolation and adds moving target protection in the procedure.This method can suppress the short-range clutter well.Simulation results show the validity of the method.展开更多
非侵入式负荷监测(non-intrusive load monitoring,NILM)技术对于实现智慧用电与管理具有重要意义。针对现有的非侵入式负荷监测方法在高噪声环境下对特征相似电器以及微小负荷变化监测精度不足的难题,提出了一种基于单位力操作视觉变...非侵入式负荷监测(non-intrusive load monitoring,NILM)技术对于实现智慧用电与管理具有重要意义。针对现有的非侵入式负荷监测方法在高噪声环境下对特征相似电器以及微小负荷变化监测精度不足的难题,提出了一种基于单位力操作视觉变换器的非侵入式负荷监测(non-intrusive load monitoring based on unit force operated vision transformer,UFONILM)模型的非侵入式负荷监测的深度学习框架。UFONILM模型的单位力操作(unit force operated,UFO)模块通过层归一化和一系列卷积层有效地提取和利用了多尺度的时间序列数据,特征。在标准的UK-DALE数据集上进行的实验显示,UFONILM模型在准确性和F1得分上均优于现有方法,特别是在细粒度的负荷监测场景中。研制了基于UFONILM模型的嵌入式系统,实现了边缘计算的非侵入式负荷监测,可实时监测和响应电网中的异常用电行为,如违规充电事件。实验检测证明,UFONILM模型嵌入式非侵入式负荷监测方法在监测效率方面具有显著的提升,具有高效、便捷安装、可扩展等特点。展开更多
基金Support by the National Natural Science Foundation of China(No.60736009 and No.60825104)
文摘When the Airborne Early Warning(AEW) radar transmits medial or high Pulse Repetitive Frequency(PRF) signal,the range ambiguity occurs.The clutter of short-range clutter has serious range dependence problem for non-Side Looking Airborne Radar(non-SLAR).As a result,the clutter plus noise covariance matrix can not be estimated correctly,and the performance of clutter suppression obtained by Space-Time Adaptive Processing(STAP) degrades greatly.The uniform linear array has not elevation degrees;therefore,the short-range clutter can not be suppressed directly.A short-range clutter suppression method is proposed.The method first estimate the elevation angles of the ambiguous short-range gate,then eliminates short-range clutter by space time interpolation and adds moving target protection in the procedure.This method can suppress the short-range clutter well.Simulation results show the validity of the method.
文摘非侵入式负荷监测(non-intrusive load monitoring,NILM)技术对于实现智慧用电与管理具有重要意义。针对现有的非侵入式负荷监测方法在高噪声环境下对特征相似电器以及微小负荷变化监测精度不足的难题,提出了一种基于单位力操作视觉变换器的非侵入式负荷监测(non-intrusive load monitoring based on unit force operated vision transformer,UFONILM)模型的非侵入式负荷监测的深度学习框架。UFONILM模型的单位力操作(unit force operated,UFO)模块通过层归一化和一系列卷积层有效地提取和利用了多尺度的时间序列数据,特征。在标准的UK-DALE数据集上进行的实验显示,UFONILM模型在准确性和F1得分上均优于现有方法,特别是在细粒度的负荷监测场景中。研制了基于UFONILM模型的嵌入式系统,实现了边缘计算的非侵入式负荷监测,可实时监测和响应电网中的异常用电行为,如违规充电事件。实验检测证明,UFONILM模型嵌入式非侵入式负荷监测方法在监测效率方面具有显著的提升,具有高效、便捷安装、可扩展等特点。
