Standard Data-Based Predictive Modeling for Power Consumption in Turning Machining

Published

February 26, 2018

Author(s)

Seungjun Shin, Jungyub Woo, Sudarsan Rachuri, Prita Meilanitasari

Abstract

In the metal cutting industry, power consumption is an important metric in the analysis of energy efficiency since it relates to energy consumption of machine tools. Much of the research has developed predictive models that correlate process planning decisions with power consumption through theoretical and/or experimental modeling approaches. These models are created by using the theory of metal cutting mechanics and Design of Experiments. However, these models may lose their ability to predict results correctly outside the required assumptions and limited experimental conditions. Thus, they cannot accurately reflect a diversity of machining configurations; i.e., selections of machine tool, workpiece, cutting tool, coolant option, and machining operation for producing a part, which a machining shop has operated. This paper proposes a predictive modeling approach based on historical data collected from machine tool operations. The proposed approach can create multiple predictive models for power consumption, which can be applicable to the diverse machining configurations. It can create fine-grained models predictable up to the level of a numerical control program. It uses standard-based data interfaces such as STEP-NC and MTConnect to implement interoperable and comprehensive data representations. This paper also presents a case study to demonstrate the feasibility and effectiveness of the proposed approach.

Citation

Sustainability

Pub Type

Journals

Download Paper

https://doi.org/10.3390/su10030598

Local Download

Keywords

power consumption, predictive model, machining, STEP-NC, MTConnectNC, MTConnect

Citation

Shin, S. , Woo, J. , Rachuri, S. and Meilanitasari, P. (2018), Standard Data-Based Predictive Modeling for Power Consumption in Turning Machining, Sustainability, [online], https://doi.org/10.3390/su10030598, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=917381 (Accessed November 25, 2025)