Towards a generalized energy prediction model for machine tools
Raunak Bhinge, Jinkyoo Park, Kincho H. Law, David Dornfeld, Moneer Helu, Sudarsan Rachuri
Energy prediction of machine tools can deliver many advantages to a manufacturing enterprise, ranging from energy-efficient process planning to machine tool monitoring. Physics-based energy prediction models have been proposed in the past to understand the energy usage pattern of a machine tool. However, uncertainties in both the machine and the operating environment make it difficult to reliably predict the energy consumption of the target machine. Taking advantage of the opportunity of collecting extensive contextual energy consumption data, this paper discusses a data-driven approach to develop an energy prediction model of a machine tool. First, a data collecting and processing methodology that can efficiently and effectively extract data from a machine tool and its sensors is discussed. We then present a data-driven energy prediction model that can be used to predict the energy consumption of the machine tool for machining a generic part. Specifically, the Gaussian Process (GP) Regression, a non-parametric machine learning technique, is employed in this study for developing the energy prediction model. The energy prediction model is then generalized over multiple process parameters and operations. We finally apply this prediction model to a Mori Seiki NVD1500 machine tool to produce energy consumption predictions with high-level confidence through uncertainty quantification. The methodology can be used to predict the energy consumption for machining any generic part on the same machine with confidence limits. Furthermore, the energy prediction model can be employed to select optimal energy efficient machining strategies and to reduce energy consumption in a machining process.
ASME Journal of Manufacturing Science and Engineering
, Park, J.
, Law, K.
, Dornfeld, D.
, Helu, M.
and Rachuri, S.
Towards a generalized energy prediction model for machine tools, ASME Journal of Manufacturing Science and Engineering, [online], https://doi.org/10.1115/1.4034933, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=919583
(Accessed December 10, 2023)