1 April 2021 in Journal of Manufacturing Systems
1 January 2020 in Advanced Engineering Informatics
8 September 2018 in International Journal of Production Research
Additive Manufacturing (AM) with its unique capabilities provides a new way of rapid product development. The emerging Cloud Manufacturing paradigm makes it much easier to access various AM resources with minimum investment. Distributed recourses can also be utilised more efficiently. However, the current cloud platforms mainly focus on providing simple 3D printing services, rather than support the customers throughout the product development process, from design, to process planning, and to printing. Therefore, a new cloud platform is proposed to integrate not only hard resources such as 3D printers and materials, but also soft resources such as the know-how and test data to provide supports on printing as well as design and process planning. Internet of Things provides new capabilities to the cloud platform, enabling customers to remotely control and monitor the printing process. The paper also examined the feasibility of Artificial Neural Networks for surface defect detection. The platform is able to work in dynamic and iterative product development processes and reduce development time and cost. An illustrative platform is developed to demonstrate the functionalities.
20 March 2017 in Rapid Prototyping Journal
Purpose: This study aims to review the existing methods for additive manufacturing (AM) process selection and evaluate their suitability for design for additive manufacturing (DfAM). AM has experienced a rapid development in recent years. New technologies, machines and service bureaus are being brought into the market at an exciting rate. While user’s choices are in abundance, finding the right choice can be a non-trivial task. Design/methodology/approach: AM process selection methods are reviewed based on decision theory. The authors also examine how the user’s preferences and AM process performances are considered and approximated into mathematical models. The pros and cons and the limitations of these methods are discussed, and a new approach has been proposed to support the iterating process of DfAM. Findings: All current studies follow a sequential decision process and focus on an “a priori” articulation of preferences approach. This kind of method has limitations for the user in the early design stage to implement the DfAM process. An “a posteriori” articulation of preferences approach is proposed to support DfAM and an iterative design process. Originality/value: This paper reviews AM process selection methods in a new perspective. The users need to be aware of the underlying assumptions in these methods. The limitations of these methods for DfAM are discussed, and a new approach for AM process selection is proposed.
21 May 2020 in IEEE/ASME Transactions on Mechatronics
Additive manufacturing has been increasingly applied. As one of the most commonly used technologies, fused deposition modeling (FDM) still faces the challenge of instable performance. The appearance of the printed part is an important feature to assess its quality. As FDM processes usually take a long time, it is very important to timely identify the defects to avoid unnecessary waste of time and cost. At current stage, this identification work is usually done by the operators. However, it is difficult to realize continuous monitoring for multiple printers and identify surface defects shortly. With the advanced artificial intelligence techniques, a vision-based adaptive monitoring system is proposed in this article to achieve online monitoring with high efficiency and accuracy. The system design is introduced for common FDM printers that allows one camera to move to different angles and capture the images of the printing part. A heuristic algorithm is then proposed to achieve adaptive shooting position planning according to the part geometries. Furthermore, a convolutional neural network-based model is designed to achieve efficient defect classification with high accuracy. A series of experiments have been conducted to illustrate the effectiveness of the proposed system.
1 August 2019 in Robotics and Computer-Integrated Manufacturing