Monitoring of the Semiconductor Wirebond Ultrasonic Signal for Prediction of Corresponding Electrical Test Result

Date of Award

2021

Document Type

Thesis

Degree Name

Master of Science in Electronics Engineering

Department

Electronics, Computer, and Communications Engineering

First Advisor

Patricia Angela R. Abu, PhD; Carlos M. Oppus, MS; Rosula S.J. Reyes, PhD

Abstract

The electronics industry is one of the largest global industries and its growing rapidly as a result of increasing demand from emerging market economies. Many international electronic companies are increasingly producing more electronics in fastest time as possible to meet the high demand and fast changing evolution of electronics. All of the electronics company goal is to produce zero defect and deliver the product on-time to meet the global high demand for electronics. This study seeks to help the manufacturing to determine/predict each production lot on its corresponding electrical test result. One production lot will be subjected to data gathering. Corresponding wire bond ultrasonic signal will be gathered using Arduino Microcontroller and fed on machine learning algorithm to detect/predict if the gathered signal will be rejected and will become possible failure at later electrical testing. This will give a heads-up to the manufacturing if the lot will be to replaced immediately to still meet the committed schedule of delivery. A key point for this study is the usage of a low-cost hardware for signal acquisition and processing. Its embedded design approach lend itself well to real-time operation. More importantly this study would provide a way for legacy manufacturing equipment to be upgraded and thus be integrated into other system that are designed for “Industry 4.0” implementation.

This document is currently not available here.

Share

COinS