Predicting alarms in manufacturing industries

Date

2023-05

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

This paper introduces a predictive algorithm designed for managing alarms in manufacturing industries. By gathering data from various sources, such as machine sensors and maintenance records, the algorithm can anticipate potential alarms and notify operators ahead of time. Unforeseen downtime can have substantial negative consequences for businesses, including revenue loss, decreased productivity, and diminished customer satisfaction. As reported by the Association for Manufacturing Technology, the average cost of unexpected downtime for a manufacturing facility amounts to $22,000 per minute, which can rapidly accumulate and significantly affect a company's profitability. This study aims to evaluate the performance of multiple machine learning algorithms, such as decision trees and random forests, in predicting alarms and identifying potential issues. The insights gained from this research will shed light on the potential advantages and limitations of employing machine learning algorithms in the manufacturing sector.

Description

Undergraduate thesis submitted to the Department of Computer Science and Information Systems, Ashesi University, in partial fulfillment of Bachelor of Science degree in Management Information Systems, May 2023

Keywords

Citation

DOI