OPTIMIZATION OF WELDING ROUTE USING REINFORCEMENT LEARNING METHOD

摘要：

A ship 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 many welding lines exist. Now automatic welding machine of simple type usinlgg truck system is applied widely as well as semi-automatic CO2 weld or gravity weld. Since the automatic welding machine needs help of workers when initial setting, turning, and shifting, the efficient routing has to be investigated for the improvement of the productivity. However, it is very difficult to find an optimal weld sequence when weld lines increases and then the combination number of welding sequence increases. Such type of research is called combinatorial problem. This paper has examined how to decrease the work time usinlgg the reinforcement learning method which imitated the behavior pattern of animals.

关键词： Optimization Welding route Reinforcement learning Welding robot Ship hull Assembly

作者: Yasuhisa Okumoto

作者单位: Kinki University, School of Engineering, Takayaumenobe, Higashihiroshima 739 - 2116 Japan

会议类型: 国际会议

会议名称: The Ninth International Conference on Industrial Management(第九届工业管理国际会议 ICIM2008)

会议地点: 日本大阪

会议语种:英文

页码: 83-88

在线出版日期: 2008-09-16（万方平台首次上网日期，不代表论文的发表时间）