An energy-efficient process planning system using machine-monitoring data: A data analytics approach

Abstract

This paper presents a system development of incorporating Computer-Aided Process Planning (CAPP) with energy-efficient machining based on a hybrid approach to take advantage of Generative Process Planning (GPP) and Variant Process Planning (VPP) and compensate for the drawbacks of both GPP and VPP. The GPP decides process plans without human assistance through decision-making algorithms in computers but lacks in ensuring the models’ robustness for different machining conditions. The VPP adopts group technology by reusing existing plans through the identification and classification of part family but does not support predictive and optimum decision-making. The developed Energy-Efficient Process Planning System (EEPPS) builds upon data analytics to efficiently process the machine-monitoring data collected from real machine tool’s operations and to develop energy prediction and optimization models based on historical machine-monitoring data. Particularly, those energy prediction and optimization models allow process planners to anticipate the energy consumed during executing a numerical control program and optimize process parameters at the level of machining features for minimizing energy use. This paper also presents a prototype implementation to show the feasibility of the proposed EEPPS.