3DP Check: A Deep Learning-Based Diagnostic Tool for Fault Monitoring in Additive Manufacturing

An agile approach to the design and development of hardware has been made possible by fast prototyping using additive manufacturing (AM). Although the procedure is short, a disadvantage would be any potential mistakes or problems that would be hard to spot. Failures that go unnoticed might harm the AM device and result in wasted output, costing more time and money. The goal of the research is to create a system that tracks 3D printing activities and forecasts printer temperature readings in the future. This article describes the creation of 3DP Check, a diagnostic tool for additive manufacturing that uses deep learning to look for errors. The system will employ a web application built on the Internet of Things (IoT) to gather real-time data from several sensors linked to an AM device. Forecasting metrics, including the root mean square error (RMSE), mean average error (MAE), symmetric mean absolute percentage error (sMAPE), and r-square (R
²
) values, will be analyzed when the model is put to the test. With an RSME of 0.4391, MAE of 0.2834, sMAPE of 0.1416, and R
²
of 0.6922, LSTM is shown to perform best after a thorough comparative examination.