Journal of the Japan Society of Naval Architects and Ocean Engineers
Online ISSN : 1881-1760
Print ISSN : 1880-3717
ISSN-L : 1880-3717
Paper
Optimization of Welding Route by Automatic Machine Using Reinforcement Learning Method
Yasuhisa OkumotoTakehisa Ogawa
Author information
JOURNAL FREE ACCESS

2007 Volume 5 Pages 85-89

Details
Abstract
A hull block is generally composed of skin plates, longitudinals and transverse webs as a grillage structure, and longitudinals and transverse webs are joined by fillet weld on a skin plate panel. Then much labour time is necessary for this welding work because of many welding lines. Then automatic welding machines of simple type using truck system are applied as well as semi-automatic CO2 weld or gravity weld at present. Since the automatic welding machines need help of workers when initial setting, turning, and shifting, the efficient routing has to be investigated for the productivity. However, it is very difficult to find an optimal weld sequence when weld line increases and then the combination number of welding sequence increases. The subject of research is so-called combinatorial problem. This paper examined how to decrease the work time using the reinforcement learning method which imitated the behavior pattern of animals.
Content from these authors
© 2007 The Japan Society of Naval Architects and Ocean Engineers
Previous article Next article
feedback
Top