A Study on Line-Balancing Using a Hopfield Neural Network for Manufacturing Processes

Abstract

A new approach using an analog type Hopfield 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 should be satisfied, and (C) the cycle-time of operations should be minimized. It is shown from the computer simulation that the network can successfully solve the line balancing problems. Furthermore, several techniques to adjust the network parameters are applied for the improvement.