Supporting manufacturing design by analytics, continuous collaborative process improvement enabled by the advanced manufacturing analytics platform

Abstract

The manufacturing industry is faced with global com petition making efficient, effective and continuously improved manufacturing processes a critical success factor. Yet, media discontinuities, the use of isolated analysis methods on local data sets as well as missing means for sharing analysis results cause a collaborative gap in Manufacturing Process Management that prohibits continuous process improvement. To address this chal lenge, this paper proposes the Advanced Manufacturing Analytics (AdMA) Platform that bridges the gap by integrating operational and process manufacturing data, defining a reposito ry for analysis results and providing indication-based and pat tern-based optimization techniques. Both the conceptual architec ture underlying the platform as well as its current implementa tion are presented in this paper.

MaXCept -- Decision Support in Exception Handling through Unstructured Data Integration in the Production Context: An Integral Part of the Smart Factory

“…The majority of unstructured data, which constitute 50 to 80% of data within an organization [34], are not accessed through analytics at all. Knowledge discovery is thus severely restricted and data-driven optimization of processes is conducted slowly if at all [12]. This means that complex, un-anticipated exceptions in realtime production which lead to flawed products or missed deadlines and thus to revenue loss may not be handled quickly and appropriately or may not even be discovered on time.…”

Analysis and optimization in smart manufacturing based on a reusable knowledge base for process performance models

“…Prescriptive analytics typically involves decision optimization techniques, such as mathematical and constraint programming. Examples of research in prescriptive analytics in manufacturing can be found in [10,11].…”

A PLM-based data analytics approach for improving product development lead time in an engineer-to-order manufacturing firm

“…It provides the necessary lifecycle context for analytics model development [8]. CRISP-DM defines six phases to complete a data analytics project and each phase further defines several key generic tasks and outputs.…”

“…The sharing and combination of analysis resulting from isolated methods and terminologies on local datasets become significantly limited [8]. This leads to high-cost and longduration development, and results in models and algorithms that are difficult to modify, extend, and reuse [9].…”