Image-based failure detection for material extrusion process using a convolutional neural network
- PDF / 12,903,095 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 45 Downloads / 260 Views
ORIGINAL ARTICLE
Image-based failure detection for material extrusion process using a convolutional neural network Hyungjung Kim 1 & Hyunsu Lee 2 & Ji-Soo Kim 2 & Sung-Hoon Ahn 2,3 Received: 24 June 2020 / Accepted: 29 September 2020 / Published online: 9 October 2020 # The Author(s) 2020
Abstract The material extrusion (ME) process is one of the most widely used 3D printing processes, especially considering its use of inexpensive materials. However, the error known as the “spaghetti-shape error,” related to filament tangling, is a common problem associated with the ME process. Once occurring, this issue, which consumes both time and materials, requires a restart of the entire process. In order to prevent this, the user must constantly monitor the process. In this research, a failure detection method which uses a webcam and deep learning is developed for the ME process. The webcam captures images and then analyzes them by machine learning based on a convolutional neural network (CNN), showing outstanding performance in both image classification and the recognition of objects. Sample images were trained based on a modified Visual Geometry Group Network (VGGNet) model and the trained model was evaluated, resulting in 97% accuracy. The pre-trained model was tested on a 3D printer monitoring system for its ability to recognize the “spaghetti-shape-error” and was able to detect 96% of abnormal deposition processes. The proposed method can analyze the ME process in real time and informs the user or halts the process when abnormal printing is detected. Keywords 3D printing process . Material extrusion . Failure detection . Process monitoring . Deep learning . Convolutional neural network
1 Introduction 1.1 Global trend about 3D printer Currently, considering the “Fourth Industrial Revolution,” 3D printing, or additive manufacturing, is ready to emerge from its niche status and become a viable alternative to conventional manufacturing processes in an increasing number of applications. In fact, it is now an enabling technology in smart factories and in cloud manufacturing [1, 2]. The advantages of 3D printing over other conventional manufacturing
Hyungjung Kim and Hyunsu Lee share equally first authorship * Sung-Hoon Ahn [email protected] 1
Sales Division, Doosan Robotics Inc., Suwon 16648, Republic of Korea
2
Department of Mechanical Engineering, Seoul National University, Seoul 08826, Republic of Korea
3
Institute of Advanced Machines and Design, Seoul National University, Seoul 08826, Republic of Korea
technologies are leading to significant changes in product development processes. This approach uses direct digital manufacturing processes that directly transform 3D data into actual parts without requiring tools or molds [3]. Additionally, the layer manufacturing principle can also produce functionally integrated parts in a single production step, reducing the need for assembly activities [4]. This technology can transform manufacturing companies by, for example, reducing the time required for product development,
Data Loading...
