Logo image
Simultaneous optimisation of the broadband tap coupler optical performance based on neural networks and exponential desirability functions
Journal article   Peer reviewed

Simultaneous optimisation of the broadband tap coupler optical performance based on neural networks and exponential desirability functions

C.-M. Hsu, C.-T. Su and D. Liao
International Journal of Advanced Manufacturing Technology, Vol.23(11-12), pp.896-902
2004

Abstract

Exponential desirability function Multi-response problem Neural network Parameter design Single-window broadband tap coupler
This study presents an integrated procedure using neural networks and exponential desirability functions to resolve multi-response parameter design problems. The proposed procedure is illustrated through optimising the parameter settings in the fused bi-conic taper process to improve the performance and reliability of the 1% (1/99) single-window broadband tap coupler. The proposed solution procedure was implemented on a Taiwanese manufacturer of fibre optic passive components and the implementation results demonstrated its practicability and effectiveness. A pilot run of the fused process revealed that the average defect rate was reduced to just 2.5%, from a previous level of more than 35%. Annual savings from implementing the proposed procedure are expected to exceed 0.5-1.0 million US dollars. This investigation has been extensively and successfully applied to develop optimal fuse parameters for other coupling ratio tap couplers.

Metrics

1 Record Views

Details

Logo image