首页|New Findings from South China University of Technology in the Area of Robotics Described (Online Fault Diagnosis of Harmonic Drives Using Semisupervised Contrastive Graph Generative Network Via Multimodal Data)
New Findings from South China University of Technology in the Area of Robotics Described (Online Fault Diagnosis of Harmonic Drives Using Semisupervised Contrastive Graph Generative Network Via Multimodal Data)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
IEEE
New research on Robotics is the subject of a report. According to news reporting out of Guangzhou, People's Republic of China, by NewsRx editors, research stated, "Harmonic drive is a core component of the industrial robot, its failure will directly affect the robot's performance. Moreover, as the harmonic drive often works with excessive speed and load, it may fail unpredictably." Financial supporters for this research include National Natural Science Foundation of China (NSFC), International Cooperation Projects of Guangzhou Development Zone, Opening Project of National and Local Joint Engineering Research Center for Industrial Friction and Lubrication Technology, National Natural Science Foundation of Guangdong Province, KEY Laboratory of Robotics and Intelligent Equipment of Guangdong Regular Institutions of Higher Education, Innovation Center of Robotics and Intelligent Equipment. Our news journalists obtained a quote from the research from the South China University of Technology, "Therefore, online fault diagnosis is quite significant. In this article, we propose an online intelligent fault diagnosis method for harmonic drives using a semisupervised contrastive graph generative network (SCGGN) via multimodal data. First, multimodal data (including motor current signals and encoder signals) of the harmonic drive are collected online. The Euclidean distance is used to analyze the similarity of the data in the frequency domain. Second, multiple graph convolution network and hierarchical graph convolution network are used to obtain complementary fault features from local and global views, respectively. Third, the contrastive learning network is constructed to obtain high-level information through unsupervised learning and perform data clustering to obtain the multiclassification output. Finally, a combination of learnable loss functions is used to optimize the SCGGN. The presented method is tested on an industrial robot."
GuangzhouPeople's Republic of ChinaAsiaEmerging TechnologiesMachine LearningRobotRoboticsSouth China University of Technology
NETL
NSTL
IEEE
