TY - GEN
T1 - Predictive usage mining for sustainability of complex systems design
AU - Ma, Jungmok
AU - Kim, Harrison M.
N1 - Publisher Copyright:
Copyright © 2014 by ASME.
PY - 2014
Y1 - 2014
N2 - A new perspective of dynamic LCA (life cycle assessment) is proposed with the predictive usage mining for sustainability (PUMS) algorithm. By defining usage patterns as trend, seasonality, and level from a time series of usage information, predictive LCA can be conducted in a real time horizon. Large-scale sensor data of product operation is analyzed in order to mine usage patterns and build a usage model for LCA. The PUMS algorithm consists of handling missing and abnormal values, seasonal period analysis, segmentation analysis, time series analysis, and predictive LCA. A newly developed segmentation algorithm can distinguish low activity periods and help to capture patterns more clearly. Furthermore, a predictive LCA method is formulated using a time series usage model. Finally, generated data is used to do predictive LCA of agricultural machinery as a case study.
AB - A new perspective of dynamic LCA (life cycle assessment) is proposed with the predictive usage mining for sustainability (PUMS) algorithm. By defining usage patterns as trend, seasonality, and level from a time series of usage information, predictive LCA can be conducted in a real time horizon. Large-scale sensor data of product operation is analyzed in order to mine usage patterns and build a usage model for LCA. The PUMS algorithm consists of handling missing and abnormal values, seasonal period analysis, segmentation analysis, time series analysis, and predictive LCA. A newly developed segmentation algorithm can distinguish low activity periods and help to capture patterns more clearly. Furthermore, a predictive LCA method is formulated using a time series usage model. Finally, generated data is used to do predictive LCA of agricultural machinery as a case study.
KW - Life cycle assessment
KW - Segmentation of time series
KW - Time series analysis
KW - Usage pattern modeling
UR - http://www.scopus.com/inward/record.url?scp=84961368877&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84961368877&partnerID=8YFLogxK
U2 - 10.1115/DETC2014-34755
DO - 10.1115/DETC2014-34755
M3 - Conference contribution
AN - SCOPUS:84961368877
T3 - Proceedings of the ASME Design Engineering Technical Conference
BT - 19th Design for Manufacturing and the Life Cycle Conference; 8th International Conference on Micro- andNanosystems
PB - American Society of Mechanical Engineers (ASME)
T2 - ASME 2014 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2014
Y2 - 17 August 2014 through 20 August 2014
ER -