TY  - MANSCPT
AU  - Muhammad Amir Aminuddin,
TI  - Trend analysis on machine downtime for preventive maintenance of computer numerical control (CNC) machine
SN  - THE0010026 (Local)
PY  - 2023///
CY  - Kuantan Pahang
PB  - UMPSA
KW  - Center for Mathematical Sciences
KW  - Dissertations
KW  - Universities and colleges
KW  - Final Year Report
N1  - Center for Mathematical Sciences; Bachelor of Applied Science In Data Analytics With Honour -- Universiti Malaysia Pahang – 2023; Includes bibliographical references
N2  - Computer Numerical Control machining is a subtractive manufacturing technique that  removes layers of material from a blank or workpiece to create a specific product. It is  widely used in numerous industries including electronics. Electronic manufacturing  organizations are facing an ever-increasing level of competition on a global scale making it an absolute requirement to decrease the amount of downtime that occurs  during production operations to maximize machine availability and productivity. To  ensure that customers' demands are met on time, downtime should be evaluated to  identify the underlying causes of the issue and mitigate its effects. The study aims to  analyze and forecast the trend of Computer Numerical Control (CNC) machine  downtime through predictive modelling using machine learning models. In this study,  eXtreme Gradient Boosting and Random Forest have been used to forecast the trend of  future downtime occurrences. Based on the results of comparative performance analysis, the study reveals that eXtreme Gradient Boosting model outperforms Random  Forest in forecasting future CNC downtime, demonstrating lower prediction errors. The  outcome of this research is an interactive dashboard that integrates the analysis of historical and forecasted CNC machine downtime trends. This effort aims to provide  valuable support to the industry by enhancing their preventive maintenance
ER  -