非侵入式负荷监测(non-intrusive load monitoring,NILM)是一种无需进入每个用电器内部系统,仅在用户总线入口处安装监测设备的技术.在开展NILM技术研究时,往往需要收集大规模的用户负荷数据来证明所提出方法的普适性,此需求不可避免地...非侵入式负荷监测(non-intrusive load monitoring,NILM)是一种无需进入每个用电器内部系统,仅在用户总线入口处安装监测设备的技术.在开展NILM技术研究时,往往需要收集大规模的用户负荷数据来证明所提出方法的普适性,此需求不可避免地带来了繁重的数据收集与整理负担.为克服该挑战,设计了一种结合周期信号频率不变变换(frequency invariant transformation for periodic signals,FIT-PS)原理与时间序列生成对抗网络(time series generative adversarial networks,TimeGAN)的混合模型,记为FIT-PSTimeGAN.针对全球家庭与工业瞬态能量数据集(worldwide household and industry transient energy dataset,WHITED)中的空调、微波炉、吸尘器、冰箱和热水壶5种电器,运用FIT-PS对负荷数据集进行切割和拼接,构建TimeGAN不同状态下的训练集和测试集.评估测试集的效果发现,生成的波形数据与真实数据表现出高度一致性.进一步采用FIT-PS对训练得到的生成数据进行截取和拼接,生成满足测试需求的完整的单负荷波形和多负荷波形.对这些生成的波形与相同状态下的真实数据进行对比,结果显示两者吻合度很高.与自回归模型和生成对抗网络(generative adversarial network,GAN)模型相比,FIT-PS-TimeGAN模型在生成数据的性能方面表现更优.研究结果表明,FIT-PS-TimeGAN混合模型能够有效生成符合标准电器运行规律的波形和场景数据.展开更多
This paper describes an automated path generation method for industrial robots. Based on force control, a robotic subsystem has been developed for path automatic generation or path learning. Using a dummy tool and rou...This paper describes an automated path generation method for industrial robots. Based on force control, a robotic subsystem has been developed for path automatic generation or path learning. Using a dummy tool and roughly taught guiding points around a part contour, the robot moves in position and force controlled hybrid mode, following the order of the guiding points and with contact force direction and value predefined. During the motion, robot actual position is recorded by the robot controller. After the motion, the recorded position data is used to generate a robot path program automatically. Robot lead-through may be used in the guiding point teaching. Furthermore, a GUI （graphical user interface） is developed on the teach pedant to guide through the guiding point creation and teaching, path learning, program verification and execution. The development has been incorporated into a robotic machining product option. Combination of the robot path learning function and GUI enhances the interaction between the robot and operator and drastically increases the level of robotic ease-of-use.展开更多
文摘非侵入式负荷监测(non-intrusive load monitoring,NILM)是一种无需进入每个用电器内部系统,仅在用户总线入口处安装监测设备的技术.在开展NILM技术研究时,往往需要收集大规模的用户负荷数据来证明所提出方法的普适性,此需求不可避免地带来了繁重的数据收集与整理负担.为克服该挑战,设计了一种结合周期信号频率不变变换(frequency invariant transformation for periodic signals,FIT-PS)原理与时间序列生成对抗网络(time series generative adversarial networks,TimeGAN)的混合模型,记为FIT-PSTimeGAN.针对全球家庭与工业瞬态能量数据集(worldwide household and industry transient energy dataset,WHITED)中的空调、微波炉、吸尘器、冰箱和热水壶5种电器,运用FIT-PS对负荷数据集进行切割和拼接,构建TimeGAN不同状态下的训练集和测试集.评估测试集的效果发现,生成的波形数据与真实数据表现出高度一致性.进一步采用FIT-PS对训练得到的生成数据进行截取和拼接,生成满足测试需求的完整的单负荷波形和多负荷波形.对这些生成的波形与相同状态下的真实数据进行对比,结果显示两者吻合度很高.与自回归模型和生成对抗网络(generative adversarial network,GAN)模型相比,FIT-PS-TimeGAN模型在生成数据的性能方面表现更优.研究结果表明,FIT-PS-TimeGAN混合模型能够有效生成符合标准电器运行规律的波形和场景数据.
文摘This paper describes an automated path generation method for industrial robots. Based on force control, a robotic subsystem has been developed for path automatic generation or path learning. Using a dummy tool and roughly taught guiding points around a part contour, the robot moves in position and force controlled hybrid mode, following the order of the guiding points and with contact force direction and value predefined. During the motion, robot actual position is recorded by the robot controller. After the motion, the recorded position data is used to generate a robot path program automatically. Robot lead-through may be used in the guiding point teaching. Furthermore, a GUI （graphical user interface） is developed on the teach pedant to guide through the guiding point creation and teaching, path learning, program verification and execution. The development has been incorporated into a robotic machining product option. Combination of the robot path learning function and GUI enhances the interaction between the robot and operator and drastically increases the level of robotic ease-of-use.
