Abstract
The agenda of Industry 4.0 highlights smart manufacturing by making machines smart enough to make data-driven decisions. Large-scale 3D printers, being one of the important pillars in Industry 4.0, are equipped with smart sensors to continuously monitor print processes and make automated decisions. One of the biggest challenges in decision autonomy is to consume data quickly along the process and extract knowledge from the printer, suitable for improving the printing process. This paper presents the innovative unsupervised learning approach, bootstrap–CURE, to decode the sensor patterns and operation modes of 3D printers by analyzing multivariate sensor data. An automatic technique to detect the suitable number of clusters using the dendrogram is developed. The proposed methodology is scalable and significantly reduces computational cost as compared to classical CURE. A distinct combination of the 3D printer’s sensors is found, and its impact on the printing process is also discussed. A real application is presented to illustrate the performance and usefulness of the proposal. In addition, a new state of the art for sensor data analysis is presented.
Highlights
IntroductionIndustry 4.0 [1] has been revolutionizing the manufacturing practices with a strong influence on mechanization and automation
When a 3D printer works in the real production environment under smart manufacturing [3], most of its activities are completely automated and governed by an electronic control system
The main contribution of the paper is to introduce a modification of the Clustering Using Representation (CURE) algorithm [63] that scales the hierarchical clustering up to big data and automatically cuts the hierarchical dendrogram so that the operation states of a certain population of printers can be identified
Summary
Industry 4.0 [1] has been revolutionizing the manufacturing practices with a strong influence on mechanization and automation. This brings up the importance of sensors and their pattern analysis. An exhaustive analysis of the data provided by sensors can help obtain crucial information about the health of the overall system, as well as developing tools for faster knowledge extraction and automation. Sensor data are typically unlabeled and demand an unsupervised methodology to characterize their impact on a machine and explainable AI techniques to interpret the results from a semantic point of view. A proper understanding of machine operations under various conditions can help answer what factors cause such problems
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
