RXRui Xiao

Rui Xiao

*This is an algorithmically generated author record based on publicly available information.

Rui Xiao has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Review on Digital Twin for Robotics in Smart Manufacturing

    by Xinquan Liang, Rui Xiao, Jingbing Zhang

    As one of the key enablers of Industry 4.0, robotics enabled automation has been increasingly deployed not only to perform dangerous, dirty, dull, and repetitive tasks, but also to support and augment human beings to address challenges associated with ageing population and labor shortages. However, the design, development, deployment, commissioning, and maintenance of robotics systems have never been trivial tasks, especially for complex robotics systems consisting of multiple heterogenous robots and other subsystems, such as manufacturing equipment, sensors, Internet of Things (IoT) gateways, smart infrastructure devices, and so on. Digital twin (DT) as a merging technology has been attracting great attentions from both researchers and industrial practitioners. Digital twin for robotics has been studied for smart manufacturing, ranging from robot-human interaction, real-time product/process inspection, production optimization, and so on. This paper provides an initial review of literatures related to digital twin for robotics. The literatures are reviewed and categorized by the enabling technologies that support the DT development, and how the DT is applied and implemented in different system life cycle stages. This review aims to provide insights of the current research work and highlight key challenges that should be addressed by future research.


  • Multifeature Extraction and Semi-Supervised Deep Learning Scheme for State Diagnosis of Converter Transformer

    by Rui Xiao, Zhanlong Zhang, Yihua Dan, Yu Yang, Zhicheng Pan, Jun Deng

    The research on intelligent diagnostic models for power transmission and transformation equipment has attracted increasing interest. In the design of practical diagnostic models, the supervised learning strategy is often used. This put forward higher requirements for the number of labeled data. However, in industrial applications, the cost of collecting a large number of relevant data and effectively labeling is high. At the same time, in the case of unknown faults, the lack of prior knowledge makes accurate classification difficult to achieve. This work designs a semi-supervised hybrid framework to diagnose the state of the converter transformer in terms of the labeled data which is limited. The framework consists of three main modules: multifeature graph generation, semi-supervised training, and soft voting decision. The graph generation module encodes the vibration signal into time, frequency, and energy graphs by calculating the Gramian angular summation fields (GASF). The semi-supervised learning module integrates unsupervised learning and supervised learning strategies trained by partial label information and data reconstruction errors. The decision-making module makes multifeature decisions through soft voting. The effectiveness of the hybrid framework is verified by comparative experiments. The experimental results show that the scheme can learn and diagnose intelligently under harsh datasets.