Data Analytics on SMT Mounter Machine with File Sharing

Chew, Ze Lin (2020) Data Analytics on SMT Mounter Machine with File Sharing. Final Year Project (Bachelor), Tunku Abdul Rahman University College.

Text Chew Ze Lin.pdf Restricted to Registered users only Download (3MB)

Abstract

Nowadays Surface Mount Technology (SMT) has been widely used to mass produce printed circuit board (PCB) and it can be said as a mature technology through many years of consummation. However, there is still a common issue that has been facing in every SMT based production line company which is the part drop. Part drop is a very serious case that happens in SMT production line and can be caused by many factors such as the nozzle defect, the leakage in the vacuum suction tube, etc. It is a time-consuming effort to troubleshoot the root cause of the part-drop event. In the past, maintenance works are carried out periodically in order to prevent the machine to break down. By doing feature extraction and analysing the data to detect the possible error happen, it is believed that this issue can be minimized, and the root cause of the part drop to happen may be determined. By using this method, the root cause of part drop can be determined in a very short period of time and the engineer or even the engineer is able to complete their job with a more efficient and effective way. In this paper, machine health monitoring for the SMT machine was proposed with the intent to analyze the condition of the machine and predict mechanical wear and failure by utilizing algorithms. The part-drop features are extracted out based on the machine logs provided by Hotayi Electronics (M) Sdn. Bhd. By applying algorithm, machine health monitoring is carry out. The threshold of the WARNING and ERROR state was determined. When exceeding the threshold, maintenance will be recommended to be carried out. At the same time, the particular nozzle with malfunction will depict a bar chart where the number of part-drop is shown. Through the bar chart generated, engineer can pinpoint the exact nozzle that is defect immediately.