Open AccessA hybrid process planning for energy-efficient machining: Application of predictive analytics
Author(s) -
Seung Jun Shin
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/635/1/012032
Subject(s) - process (computing) , computer science , machining , metric (unit) , analytics , energy consumption , reuse , predictive analytics , energy (signal processing) , machine learning , engineering , data mining , mechanical engineering , operations management , electrical engineering , mathematics , waste management , operating system , statistics
Computer-aided process planning for energy-efficient machining is essential as energy consumption becomes a major environmental metric in the metal cutting industry. This paper introduces a process planning approach that enables energy prediction in the process planning phase through incorporating Generative Process Planning (GPP) and Variant Process Planning (VPP), called Hybrid Process Planning. GPP is used to provide decision making algorithms in computers by generating energy prediction models specific for machining conditions. VPP is adopted to reuse existing process plans with inclusion of such prediction models so that process planners can anticipate the energy values to be consumed in machine tools. Particularly, the present approach builds upon predictive analytics to efficiently handle sensor-level data collected from real machining operations, and create energy prediction models by using a machine-learning technique.