Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 5 of 5
Full-Text Articles in Engineering
Tandem Gas Metal Arc Welding For Low Distortion Butt Welds, Nathan Larkin, Zengxi Pan, Stephen Van Duin, Mark Callaghan, Huijun Li, John Norrish
Tandem Gas Metal Arc Welding For Low Distortion Butt Welds, Nathan Larkin, Zengxi Pan, Stephen Van Duin, Mark Callaghan, Huijun Li, John Norrish
zengxi pan
The feasibility of using Tandem Gas Metal Arc Welding (T-GMAW) to produce full penetration butt welds in 5mm ship panel steel plates has been assessed and compared to the current Submerged Arc Welding (SAW) process. Experiments conducted show that the T-GMAW process is feasible and demonstrated a significant improvement over the SAW process in several areas including higher travel speed, a reduction in filler material, significantly lower post weld distortion, and a smaller Heat Affected Zone (HAZ), while maintaining similar microstructure and mechanical properties in the weld metal and HAZ.
Autonomous Blimp Control Using Reinforcement Learning, Yiwei Liu, Zengxi Pan, David Stirling, Fazel Naghdy
Autonomous Blimp Control Using Reinforcement Learning, Yiwei Liu, Zengxi Pan, David Stirling, Fazel Naghdy
zengxi pan
This paper presents a new approach for navigation control of an autonomous blimp using an intelligent reinforcement learning algorithm. Compared to the traditional model based control methods, this control strategy does not require a dynamic model of the blimp, which provides huge advantage in many practical situations where the blimp system model is either hard to acquire or too complicated to apply. As the blimp will acquire a range of the pilot skills through a learning and rewarding mechanism during actual navigation trials, it can automatically account for the environmental changes during the navigation. The simulation data generated from a …
Automated Assembly Of Ship Panels Using An Integrated Robotic Tool, Kamran Shafiee, Zengxi Pan, Stephen Van Duin, Nathan Larkin
Automated Assembly Of Ship Panels Using An Integrated Robotic Tool, Kamran Shafiee, Zengxi Pan, Stephen Van Duin, Nathan Larkin
zengxi pan
In this paper we developed a novel and cost effective automated system for use in the Australian shipbuilding industry. We began by investigating current shipbuilding processes and determining the most feasible area where automation could be further developed. Then we designed an automation concept with the objective of developing a highly flexible system. A prototype of the integrated tool was developed for preliminary testing in a simulated industry assembly process, the results of which were benchmarked against a manually fabricated assembly. The outcomes from the benchmarking showed the feasibility of such a system and allowed us to determine the future …
Human Motion Capture Sensors And Analysis In Robotics, Matthew Field, Zengxi Pan, David Stirling, Fazel Naghdy
Human Motion Capture Sensors And Analysis In Robotics, Matthew Field, Zengxi Pan, David Stirling, Fazel Naghdy
zengxi pan
Purpose – The purpose of this paper is to provide a review of various motion capture technologies and discuss the methods for handling the captured data in applications related to robotics. Design/methodology/approach – The approach taken in the paper is to compare the features and limitations of motion trackers in common use. After introducing the technology, a summary is given of robotic-related work undertaken with the sensors and the strengths of different approaches in handling the data are discussed. Each comparison is presented in a table. Results from the author's experimentation with an inertial motion capture system are discussed based …
3d Mapping Using A Tof Camera For Self Programming An Industrial Robot, N Larkin, Zengxi Pan, S Van Duin, J Norrish
3d Mapping Using A Tof Camera For Self Programming An Industrial Robot, N Larkin, Zengxi Pan, S Van Duin, J Norrish
zengxi pan
Automated Offline Programing (AOLP) is a cost effective robot programming method. However, it relies on accurate CAD information of the work environment to perform optimally. Incorrect CAD data is a known source of error for AOLP systems. This paper introduces a new sensor based method of programming that extends the concept of AOLP. Using a ToF camera to map the environment, there is no reliance on CAD data. The problem of motion planning to efficiently map the environment is examined and changes to the motion planning algorithm are proposed and tested.