Surface-mount device design cycle time reduction using hybrid predictive modeling and optimization algorithm

Abstract

This study develops a hybrid predictive and optimization model for surface-mount device (SMD) design, addressing the extended design cycle times in the semiconductor industry caused by high computational demands. Challenges are tackled effectively through integration of convolutional neural network (CNN) for high-accuracy predictions and simulated annealing (SA) algorithm for optimization of SMD physical parameters. CNN model that trained on Monte Carlo simulation (MCS) data, achieved a predictive accuracy of 99.91% in forecasting SMD design errors. Concurrently, SA algorithm refined design parameters and substantially reducing error rates to nearly zero after 800 iterations. Our results indicate that combining predictive modeling with an optimization algorithm significantly enhances SMD design efficiency, providing a robust tool for mitigating time-to-market risks in semiconductor manufacturing.