A NEURAL NETWORK MODEL FOR THE HANDLING TIME OF DESIGN FOR ASSEMBLY

ABSTRACT

Motion time study has been popularly used in time measurement of product Design For Assembly (DFA). However, it takes a lot effort to develop the estimated time of manual handling and insertion. In this paper, we propose a new methodology called neural networks to predict the estimated time. Back-Propagation Networks (BPN) is employed to model the problem. The proposed neural networks is trained with an optimum experimental data, tested and compared in an actual data. Finally, it is found that the proposed method is superior in computation time and feature matching performances. A simple example is also presented in this paper. The results of this example have shown that the proposed method is suitable to assembly time estimation.

Keywords:

• design for assembly (DFA)
• time measurements
• back-propagation networks (BPN)
• neural networks
• neuroshell 2