Faults during operation of a system can occur at any time. Contemporary fault diagnosis systems focus on identifying the problem. However, when faults occur, the system has already incurred losses, either as rejects or machine damage. In this paper, a new method that predicts future faults and subsequently prevents losses caused by the faults has been developed. The method makes use of a series of digital transformations of signals from the manufacturing process. An important finding of this research is to divide the continuous signal stream into data segments from which a parameter called sum standard deviation frequency (SSDF) can be extracted. SSDF reflects the change of inconspicuous conditions in the signal in different data segments over time. To predict how the signal stream will perform in the next minute, a new density peak clustering computational algorithm is developed to transform the SSDF database into “normal”, “marginal”, and “abnormal” records. Finally, a novel method “moving SSDF deep learning” (MSDL) concept has been proven to have a better prediction of future capability than four other prediction methods. The method has been applied to a 3D printing process in which belt tension affecting machine performance has been predicted 30 s ahead of the problem, giving sufficient time for the operator to adjust or stop the machine before a fault occurs.

Globalisation has forced companies to work together in a new arrangement known as virtual enterprise. An Australian initiative called RELINK aims to demonstrate the methodologies and systems, that will enable small firms in the tooling and automotive industry to participate with medium and large firms in turnkey projects as part of a broader supply chain. The initiative draws on this body of knowledge in conjunction with research and university partners and concentrates on the practicality of the formation of virtual enterprises in the tooling and automotive industries competing with larger toolmaking companies globally. This paper explores a 5 layer open communication framework for virtual enterprise to establish a continuity of functionality in the communication process that enables B2B operations within a virtual enterprise with varying levels of communication capabilities. The framework identifies options for bridging gaps in communication functionality between the desired application level and the varying situations of the participants.

Companies can now make use of the Internet to communicate or do business. In the manufacturing industry, especially at the early phase of product development, this technology has become essential for enabling designers, process planning engineers, and production personnel to work on a consistent set of product information that is primarily CAD models. This article presents a three-tier client/server structure on which a tool is built to visualize CAD-neutral formats. This tool allows users to gather CAD models from local disks, WWW servers, and others on the company's Intranet, and then assemble and display them on the local screen. Through this facility, users can modify and save a CAD model into a database so that all project participants can work on the same set of information. The tool is platform independent with superior local 3D manipulation capabilities and supports DXF, OBJ, and VRML formats.