Quality Monitoring of 3D Printed Scaffold

As the utilization of the technology of 3D printing continues to grow in various industries, the need for quality monitoring has become increasingly important as early detection of errors in the printing process can help save time and prevent wastage of resources and labor. The process of printing in three dimensions is a complex process that involves many variables, and any deviation from the ideal printing parameters can lead to defects and substandard products. However, an adequate quality monitoring method can adequately avail for early detection and correction of such deviations during the printing process, resulting in higher quality products and increased efficiency. The literature review conducted in this study examines various techniques for quality monitoring, including optical, thermal, and acoustic methods, and identifies their strengths and limitations. Optical methods, such as laser scanning, are effective in detecting surface defects, while thermal methods, such as thermal imaging, can detect internal defects in the printed product. Acoustic methods, such as ultrasonic sensing, can detect defects by analyzing sound waves generated during the printing process. However, each technique has limitations, and the method to be chosen depends on the application it is required for. This experimental study involves the development of a prototype system for quality monitoring in 3D printing, using the method of computer vision consolidated with machine learning. The study entailed the creation of a prototype Graphical user interface that analyses the quality of image data of parts from a 3D printer, and the results show that it is effective in detecting surface defects and dimensional deviations in quasi real-time. However, the study also identifies several challenges and limitations that will engender widespread adoption of process quality monitoring in the manufacturing industry when they are addressed adequately.