Additive Manufacturing (AM) is becoming data-intensive. The ability to identify Data Analytics (DA) opportunities for effective use of AM data becomes a critical factor in the success of AM. To successfully identify high-potential DA opportunities in AM requires a set of distinctive interdisciplinary knowledge. This paper proposes a methodology that enables collaborative knowledge management for identifying and prioritizing DA opportunities in AM. The framework of the proposed methodology has three components: a team of experts, a DA Opportunity Knowledge Base (DOKB), and a prioritization tool. The team of experts provides diverse knowledge that can be used to identify and prioritize DA opportunities. The DOKB, developed by using the Web Ontology Language (OWL), captures diverse knowledge from the experts to identify DA opportunities. The prioritization tool ranks the identified DA opportunities by using the Fuzzy integrated Technique of Order Preference Similarity to the Ideal Solution (Fuzzy-TOPSIS). A case study, in which National Institute of Standards and Technology (NIST) researchers participated, demonstrates our methodology. As a result, 264 DA opportunities for AM's Laser-Powder Bed Fusion (L-PBF) process are identified and prioritized. The prioritized DA opportunities help set a DA direction for L-PBF AM. Our methodology keeps knowledge sharable, reusable, revisable, and extendable. Thus, this methodology can continue to facilitate collaboration within the AM community to identify high potential and high impact DA opportunities in AM.
Additive manufacturing (AM) is rapidly transitioning to an accepted production technology. This transition has led to increasing demands on data analysis and software tools. Advances in data acquisition and analysis are being propelled by an increase in new types of in-situ sensors and ex-situ measurement devices. Measurements taken with these sensors and devices rapidly increasing the volume, variety, and value of AM data but decreasing the veracity of that data simultaneously. The number of new, data-driven software tools capable of analyzing, modeling, simulating, integrating, and managing that data is also increasing; however, the capabilities and accessibility of these tools vary greatly. Issues associated with these software tools are impacting the ability to manage and control AM processes and qualify the resulting parts. This paper investigates and summarizes the available software tools and their capabilities. Findings are then used to help derive a set of functional requirements for tools that are mapped to AM lifecycle activities. The activities include product design, design analysis, process planning, process monitoring, process modeling, process simulation, and production management. AM users can benefit from tools implementing these functional requirements implemented by (1) shortening the lead time of developing these capabilities, (2) adopting emerging, state-of-the-art, AM data and data analytics methods, and (3) enhancing the previously mentioned AM-product-lifecycle activities.
Predictive maintenance is a maintenance strategy of diagnosing and prognosing a machine based on its condition. Compared with other maintenance strategies, the predictive maintenance strategy has the advantage of lowering the maintenance cost and time. Thus, many studies have been conducted to develop a predictive maintenance model based on a growth of prediction methodology. However, these studies tend to focus on building the predictive model and measuring its performance, rather than selecting the appropriate components for predictive maintenance. Nevertheless, selecting the predictive maintenance policy and target component are as important as model selection and performance measurement. In this paper, a selection method is proposed to improve component selection by referencing current literature and industry expert knowledge. The results of this research can serve as a foundation for further studies in this area.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.