In order to study how welding parameters affect welding quality and droplet transfer, a synchronous acquisition and analysis system is established to acquire and analyze electrical signal and instantaneous images of d...In order to study how welding parameters affect welding quality and droplet transfer, a synchronous acquisition and analysis system is established to acquire and analyze electrical signal and instantaneous images of droplet transfer simultaneously, which is based on a self-developed soft-switching inverter. On the one hand, welding current and voltage signals are acquired and analyzed by a self-developed dynamic wavelet analyzer. On the other hand, images are filtered and optimized after they are captured by high-speed camera. The results show that instantaneous waveforms and statistical data of electrical signal contribute to make an overall assessment of welding quality, and that optimized high-speed images allow a visual and clear observation of droplet transfer process. The analysis of both waveforms and images leads to a further research on droplet transfer mechanism and provides a basis for precise control of droplet transfer.展开更多
The wavelet approach is introduced to study the influence of the natural convection stagnation point flow of the Williamson fluid in the presence of thermophysical and Brownian motion effects. The thermal radiation ef...The wavelet approach is introduced to study the influence of the natural convection stagnation point flow of the Williamson fluid in the presence of thermophysical and Brownian motion effects. The thermal radiation effects are considered along a permeable stretching surface. The nonlinear problem is simulated numerically by using a novel algorithm based upon the Chebyshev wavelets. It is noticed that the velocity of the Williamson fluid increases for assisting flow cases while decreases for opposing flow cases when the unsteadiness and suction parameters increase, and the magnetic effect on the velocity increases for opposing flow cases while decreases for assisting flow cases. When the thermal radiation parameter, the Dufour number, and Williamson’s fluid parameter increase, the temperature increases for both assisting and opposing flow cases. Meanwhile, the temperature decreases when the Prandtl number increases. The concentration decreases when the Soret parameter increases, while increases when the Schmidt number increases. It is perceived that the assisting force decreases more than the opposing force. The findings endorse the credibility of the proposed algorithm, and could be extended to other nonlinear problems with complex nature.展开更多
针对轴承故障特征提取能力不足、源域与目标域数据分布差异过大等问题,本文提出了一种基于小波包域对抗注意力迁移学习的故障诊断方法(WWRESE-IDALM)。首先,通过小波包变换(Wavelet Packet Transform,WPT)获得不同重点节构的时频域信息...针对轴承故障特征提取能力不足、源域与目标域数据分布差异过大等问题,本文提出了一种基于小波包域对抗注意力迁移学习的故障诊断方法(WWRESE-IDALM)。首先,通过小波包变换(Wavelet Packet Transform,WPT)获得不同重点节构的时频域信息;其次,将重构后的时频域信息数据经过一层大卷积核和通道注意力模块(Squeeze and Excitation,SE)提取轴承深度关键信息特征;利用改进的域对抗网络(Domain-Adversarial Training of Neural Networks,DANN)和局部最大平均差异(Local Maximum Mean Discrepancy,LMMD)对齐子域分布,减少相关子域和全局域之间的结构差异;最后,通过标签分类网络完成故障分类。在帕德博恩大学轴承数据集诊断结果证明了所提出的WWRESE-IDALM方法具有良好的变工况故障分类能力。展开更多
基金This work was supported by National Natural Science Foundation of China （ No. 50875088） Natural Science Foundation of Guangdong Province, China （ No. 07006479）.
文摘In order to study how welding parameters affect welding quality and droplet transfer, a synchronous acquisition and analysis system is established to acquire and analyze electrical signal and instantaneous images of droplet transfer simultaneously, which is based on a self-developed soft-switching inverter. On the one hand, welding current and voltage signals are acquired and analyzed by a self-developed dynamic wavelet analyzer. On the other hand, images are filtered and optimized after they are captured by high-speed camera. The results show that instantaneous waveforms and statistical data of electrical signal contribute to make an overall assessment of welding quality, and that optimized high-speed images allow a visual and clear observation of droplet transfer process. The analysis of both waveforms and images leads to a further research on droplet transfer mechanism and provides a basis for precise control of droplet transfer.
基金Project supported by the National Natural Science Foundation of China(Nos.51709191,51706149,and 51606130)the Key Laboratory of Advanced Reactor Engineering and Safety,Ministry of Education of China(No.ARES-2018-10)the State Key Laboratory of Hydraulics and Mountain River Engineering of Sichuan University of China(No.Skhl1803)
文摘The wavelet approach is introduced to study the influence of the natural convection stagnation point flow of the Williamson fluid in the presence of thermophysical and Brownian motion effects. The thermal radiation effects are considered along a permeable stretching surface. The nonlinear problem is simulated numerically by using a novel algorithm based upon the Chebyshev wavelets. It is noticed that the velocity of the Williamson fluid increases for assisting flow cases while decreases for opposing flow cases when the unsteadiness and suction parameters increase, and the magnetic effect on the velocity increases for opposing flow cases while decreases for assisting flow cases. When the thermal radiation parameter, the Dufour number, and Williamson’s fluid parameter increase, the temperature increases for both assisting and opposing flow cases. Meanwhile, the temperature decreases when the Prandtl number increases. The concentration decreases when the Soret parameter increases, while increases when the Schmidt number increases. It is perceived that the assisting force decreases more than the opposing force. The findings endorse the credibility of the proposed algorithm, and could be extended to other nonlinear problems with complex nature.
文摘针对轴承故障特征提取能力不足、源域与目标域数据分布差异过大等问题,本文提出了一种基于小波包域对抗注意力迁移学习的故障诊断方法(WWRESE-IDALM)。首先,通过小波包变换(Wavelet Packet Transform,WPT)获得不同重点节构的时频域信息;其次,将重构后的时频域信息数据经过一层大卷积核和通道注意力模块(Squeeze and Excitation,SE)提取轴承深度关键信息特征;利用改进的域对抗网络(Domain-Adversarial Training of Neural Networks,DANN)和局部最大平均差异(Local Maximum Mean Discrepancy,LMMD)对齐子域分布,减少相关子域和全局域之间的结构差异;最后,通过标签分类网络完成故障分类。在帕德博恩大学轴承数据集诊断结果证明了所提出的WWRESE-IDALM方法具有良好的变工况故障分类能力。
