Predictive analytics for manufacturing sustainability performance

Published

June 20, 2014

Author(s)

Seungjun Shin, Jungyub Woo, Sudarsan Rachuri

Abstract

The Smart Manufacturing (SM) system should be capable of handling high volume data, process high velocity data and manipulate high variety data. Big data analytics can enable timely and accurate insights using machine learning and predictive analytics to make the best possible decisions. The objective of this paper is to: 1) identify a SM-driven shop floor and manufacturing data to be analyzed, 2) design a functional architecture for realizing the SM-driven shop floor, and 3) design the analytics model to predict sustainability performance, especially energy consumption in the big data infrastructure. We will describe a prototype system using open platform solutions including MapReduce, Hadoop File Distribution System, and machine learning tools. We will use STEP-NC (a standard that enables the exchange of design-to-manufacturing data, specially machining) and MTConnect that enables manufacturers to acquire machine monitoring information during runtime to test our prototype system.

Proceedings Title

Procedia CIRP

Conference Dates

June 18-20, 2014

Conference Location

Trondheim

Conference Title

21st CIRP Conference on Life Cycle Engineering

Pub Type

Conferences

Download Paper

Local Download

Keywords

sustainable manufacturing, sustainability indicator, big data, STEP-NC, MTConnect, machine learning

Citation

Shin, S. , Woo, J. and Rachuri, S. (2014), Predictive analytics for manufacturing sustainability performance, Procedia CIRP, Trondheim, -1, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=915126 (Accessed May 7, 2026)

Additional citation formats