제어로봇시스템학회:학술대회논문집

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지

Line balancing using a Hopfield network

  • Hashimoto, Yasunori (Ritsumeikan University, Department of Computer Science and Systems Engineering) ;
  • Nishikawa, Ikuko (Ritsumeikan University, Department of Computer Science and Systems Engineering) ;
  • Watanabe, Tohru (Ritsumeikan University, Department of Computer Science and Systems Engineering) ;
  • Tokumaru, Hidekatu (Ritsumeikan University, Department of Computer Science and Systems Engineering)
  • Published : 1993.10.01
Download PDF
⟨ Previous Next ⟩

Abstract

A new approach using a Hopfield type neural network to solve line balancing problems for manufacturing planning is proposed. The energy function of the network to evaluate solutions is composed of three terms;(a) an operation should be processed at one and only one workstation, (b) the precedence-relationship between two operations shoud be satisfied, and (c) the cycle-time of operations should be minimized. It is shown that the network can solve the line balancing problems but not always because of the difficulty to keep the precedence-relationship. Therefore, a method to keep the precedence-relationship by software logic is proposed and it is verified that the line-balancing prblems can be solved with high probability.

Keywords