SWShihao Wu

Shihao Wu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Shihao Wu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:

  • Jiayong Cao

    School of Mechanical Engineering, Shanghai Institute of Technology, Shanghai, China

    2 shared publications
  • Qianli Ma

    South China University of Technology, Guangzhou, China

    2 shared publications
  • Jiawei Zheng

    School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, China

    1 shared publication
  • Ru Chen

    School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, China

    1 shared publication
  • Shoujin Lin

    Zhongshan MLTOR CNC Technology Co., Ltd, Zhongshan, China

    1 shared publication
  • Song Yan

    School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, China

    1 shared publication

Latest Publications

  • Tool remaining useful life prediction considering wear state based on hybrid attention network

    by Shihao Wu, Yang Li, Weiguang Li, Xuezhi Zhao, Jiawei Zheng, Ru Chen, Song Yan, Shoujin Lin

    Accurate prediction of the remaining useful life for the cutting tool is a key part of the predictive maintenance of computer numerical control machines. However, the wide variety of tools makes the process of modeling different tool wear regularities redundant and cumbersome. In addition, it is difficult to deal with the input characteristics of multi-sensor monitoring signals in a targeted manner. To solve the above problems, a hybrid predictive model with squeeze-and-excitation (SE) module is proposed. Combined with adaptive feature extraction based on convolutional neural network and observation based on bidirectional gated recurrent unit, accurate multivariate regression prediction is achieved. The SE module enhances the focus on crucial features. Finally, through the design of the tool wear experiment and the combination of the public dataset, the accuracy and generalization ability of the proposed model are verified under different tool types and different working conditions.


  • Behavior Prediction of Vespa Mandarinia Based on Convolutional Neural Networks

    by Shihao Wu

    Vespa mandarinia poses a significant threat to honey bees and beekeepers. This paper aims to accurately predict the presence and behavior of Vespa mandarinia to enable effective control strategies. We develop an “Asian hornet queen prediction model” to forecast the dispersal path and number of queens, identifying their concentration in Bellingham, Washington, and Bellingham, Canada. Using a convolutional neural network, we achieve 96.13% accuracy in identifying Vespa mandarinia images. Analyzing confidence levels of unprocessed and unverified labels reveals a significant number of high-confidence samples. Incorporating human control factors into the model, we find 60% human intervention to be most effective in reducing the number of Asian hornet queens. Ultimately, our research highlights the potential for anthropological or ecological measures to eliminate Vespa mandarinia populations, aiding in resource allocation for proactive management.

  • Design and Experiment of Semi-Autonomous Operation Platform Assisted by Teleoperation

    by Qianli Ma, Jiayong Cao, Shihao Wu, Xing Chen

    In view of the shortage of manpower in complex and dangerous environment, a system configuration of semiautonomous teleoperation equipment which contains a master terminal, a slaver terminal and networks was put forward. In the slave terminal, a binocular vision camera was used for extracting the scope and contours of the objects on the platform. And a three-degree-of-freedom (DOF) force sensor was adopted to detect the force acting on the end effect of the robot or machine tool. The whole platform was controlled by a computer in which some Lab Viewalgorithms and Python algorithms were implemented. In the master terminal, a joystick was connected to a computer for obtaining the posture of the operator. The force and visual information generated from the force sensor and visual sensor in the remote platform was feedback to the master terminal through a local Ethernet. On the other side, the orders given by the operator to assist the remote platform was also transmitted through the same networks. An experiment testbed was established for verifying the proposed semi-autonomous teleoperation system. The experiment results show that the proposed scheme and measures are feasible in some certain.


  • Forward Position Analysis of Parallel Mechanisms in Novint Falcon Haptic Device

    by Xing Chen, Jiayong Cao, Shihao Wu, Qianli Ma

    Novint Falcon haptic device has been widely used in robot teleoperation, game, virtual reality man-machine interface and other fields. However, the existing research basis of analytical solution analysis of forward kinematics of Novint Falcon haptic device is not discussed. The forward kinematics expression of the haptic device was deduced. Given a set of forward kinematics input angles, a forward position kinematics simulation is performed. It provides a theoretical basis for the work space analysis, structural parameters optimization, trajectory planning, dynamics and motion control of the haptic device.