TY - GEN
T1 - Semi-supervised learning with co-training for data-driven prognostics
AU - Hu, Chao
AU - Youn, Byeng D.
AU - Kim, Taejin
PY - 2012
Y1 - 2012
N2 - Traditional data-driven prognostics often requires a large amount of failure data for the offline training in order to achieve good accuracy for the online prediction. However, in many engineered systems, failure data are fairly expensive and time-consuming to obtain while suspension data are readily available. In such cases, it becomes essentially critical to utilize suspension data, which may carry rich information regarding the degradation trend and help achieve more accurate remaining useful life (RUL) prediction. To this end, this paper proposes a co-training-based data-driven prognostic algorithm, denoted by Cop rog, which uses two individual data-driven algorithms with each predicting RULs of suspension units for the other. The confidence of an individual data-driven algorithm in predicting the RUL of a suspension unit is quantified by the extent to which the inclusion of that unit in the training data set reduces the sum square error (SSE) in RUL prediction on the failure units. After a suspension unit is chosen and its RUL is predicted by an individual algorithm, it becomes a virtual failure unit that is added to the training data set. Results obtained from two case studies suggest that Coprog gives more accurate RUL predictions compared to any individual algorithm without the consideration of suspension data and that Coprog can effectively exploit suspension data to improve the accuracy in data-driven prognostics.
AB - Traditional data-driven prognostics often requires a large amount of failure data for the offline training in order to achieve good accuracy for the online prediction. However, in many engineered systems, failure data are fairly expensive and time-consuming to obtain while suspension data are readily available. In such cases, it becomes essentially critical to utilize suspension data, which may carry rich information regarding the degradation trend and help achieve more accurate remaining useful life (RUL) prediction. To this end, this paper proposes a co-training-based data-driven prognostic algorithm, denoted by Cop rog, which uses two individual data-driven algorithms with each predicting RULs of suspension units for the other. The confidence of an individual data-driven algorithm in predicting the RUL of a suspension unit is quantified by the extent to which the inclusion of that unit in the training data set reduces the sum square error (SSE) in RUL prediction on the failure units. After a suspension unit is chosen and its RUL is predicted by an individual algorithm, it becomes a virtual failure unit that is added to the training data set. Results obtained from two case studies suggest that Coprog gives more accurate RUL predictions compared to any individual algorithm without the consideration of suspension data and that Coprog can effectively exploit suspension data to improve the accuracy in data-driven prognostics.
KW - Co-training
KW - Data-driven prognostics
KW - RUL prediction
KW - Semi-supervised learning
KW - Suspension data
UR - https://www.scopus.com/pages/publications/84868220704
U2 - 10.1109/ICPHM.2012.6299526
DO - 10.1109/ICPHM.2012.6299526
M3 - Conference paper
AN - SCOPUS:84868220704
SN - 9781467303569
T3 - PHM 2012 - 2012 IEEE Int. Conf.on Prognostics and Health Management: Enhancing Safety, Efficiency, Availability, and Effectiveness of Systems Through PHM Technology and Application, Conference Program
BT - PHM 2012 - 2012 IEEE Int. Conf. on Prognostics and Health Management:Enhancing Safety, Efficiency, Availability, and Effectiveness of Systems Through PHM Technology and Application,Conference Program
T2 - 2012 IEEE International Conference on Prognostics and Health Management: Enhancing Safety, Efficiency, Availability, and Effectiveness of Systems Through PHM Technology and Application, PHM 2012
Y2 - 18 June 2012 through 21 June 2012
ER -