Visual Analytics as an Enabler for Manufacturing Process Decision-making

Danielle Soban, David Thornhill, Santosh Salunkhe, Alastair Long

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)
402 Downloads (Pure)


The goal of an optimal manufacturing process is to maximize product performance while minimizing cost, time, and waste. A critical component of this optimization is the appropriate selection of process parameters. While central physical concepts often serve as a starting point, specific parameter selection is frequently done manually, based on operator skill, experience, and intuition. As a result, process optimization is often iterative, non-repeatable, and lacking in traceability. Further, there is no fundamental insight gained into the relationship between process parameter selection and critical process outputs. This paper explores the use of visual analytics as an enabler for manufacturing process decision making. An emerging science, visual analytics couples analytical reasoning with the substantial capability of the human brain to rapidly internalize and understand data that is presented visually. Through the use of interactive interfaces, visual analytics provides a mechanism through which the operator, engineer, and decision-maker can cooperate in real-time with both simulation, experimental, and operational data, facilitating trade studies, what-if analysis, and providing crucial insight into correlations and relationships that drive process optimization. As an exemplar, the concept of visual analytics is applied to the simulation of a notional high pressure die casting process, with the goal of gaining insight into those parameters that contribute to high scrap rates, particularly air entrapment.
Original languageEnglish
Pages (from-to)209-214
Number of pages6
JournalProcedia CIRP
Publication statusPublished - 16 Nov 2016


  • High Pressure Die Cating, visual analytics, manufacturing, decision-making


Dive into the research topics of 'Visual Analytics as an Enabler for Manufacturing Process Decision-making'. Together they form a unique fingerprint.

Cite this