Data driven prognostics with lack of training data sets

Zhimin Xi, Xiangxue Zhao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Data-driven prognostics typically requires sufficient offline training data sets for accurate remaining useful life (RUL) prediction of engineering products. This paper investigates performances of typical data-driven methodologies when the amount of training data sets is insufficient. The purpose is to better understand these methodologies especially when offline training datasets are insufficient. The neural network, similarity-based approach, and copula-based sampling approach were investigated when only three run-to-failure training units were available. The example of lithium-ion (Li-ion) battery capacity degradation was employed for the demonstration.

Original languageEnglish (US)
Title of host publication41st Design Automation Conference
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791857076
DOIs
StatePublished - Jan 1 2015
EventASME 2015 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2015 - Boston, United States
Duration: Aug 2 2015Aug 5 2015

Publication series

NameProceedings of the ASME Design Engineering Technical Conference
Volume2A-2015

Other

OtherASME 2015 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2015
CountryUnited States
CityBoston
Period8/2/158/5/15

Fingerprint

Data-driven
Demonstrations
Sampling
Neural networks
Degradation
Lithium-ion Battery
Life Prediction
Methodology
Copula
Neural Networks
Sufficient
Engineering
Unit
Training
Lithium-ion batteries

All Science Journal Classification (ASJC) codes

  • Modeling and Simulation
  • Mechanical Engineering
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Keywords

  • Copula-based sampling approach
  • Data-driven
  • Neural network
  • Prognostics
  • Similarity-based approach

Cite this

Xi, Z., & Zhao, X. (2015). Data driven prognostics with lack of training data sets. In 41st Design Automation Conference (Proceedings of the ASME Design Engineering Technical Conference; Vol. 2A-2015). American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/DETC201546932
Xi, Zhimin ; Zhao, Xiangxue. / Data driven prognostics with lack of training data sets. 41st Design Automation Conference. American Society of Mechanical Engineers (ASME), 2015. (Proceedings of the ASME Design Engineering Technical Conference).
@inproceedings{637aae42f6704c1c9c094517ef36a150,
title = "Data driven prognostics with lack of training data sets",
abstract = "Data-driven prognostics typically requires sufficient offline training data sets for accurate remaining useful life (RUL) prediction of engineering products. This paper investigates performances of typical data-driven methodologies when the amount of training data sets is insufficient. The purpose is to better understand these methodologies especially when offline training datasets are insufficient. The neural network, similarity-based approach, and copula-based sampling approach were investigated when only three run-to-failure training units were available. The example of lithium-ion (Li-ion) battery capacity degradation was employed for the demonstration.",
keywords = "Copula-based sampling approach, Data-driven, Neural network, Prognostics, Similarity-based approach",
author = "Zhimin Xi and Xiangxue Zhao",
year = "2015",
month = "1",
day = "1",
doi = "10.1115/DETC201546932",
language = "English (US)",
series = "Proceedings of the ASME Design Engineering Technical Conference",
publisher = "American Society of Mechanical Engineers (ASME)",
booktitle = "41st Design Automation Conference",

}

Xi, Z & Zhao, X 2015, Data driven prognostics with lack of training data sets. in 41st Design Automation Conference. Proceedings of the ASME Design Engineering Technical Conference, vol. 2A-2015, American Society of Mechanical Engineers (ASME), ASME 2015 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2015, Boston, United States, 8/2/15. https://doi.org/10.1115/DETC201546932

Data driven prognostics with lack of training data sets. / Xi, Zhimin; Zhao, Xiangxue.

41st Design Automation Conference. American Society of Mechanical Engineers (ASME), 2015. (Proceedings of the ASME Design Engineering Technical Conference; Vol. 2A-2015).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Data driven prognostics with lack of training data sets

AU - Xi, Zhimin

AU - Zhao, Xiangxue

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Data-driven prognostics typically requires sufficient offline training data sets for accurate remaining useful life (RUL) prediction of engineering products. This paper investigates performances of typical data-driven methodologies when the amount of training data sets is insufficient. The purpose is to better understand these methodologies especially when offline training datasets are insufficient. The neural network, similarity-based approach, and copula-based sampling approach were investigated when only three run-to-failure training units were available. The example of lithium-ion (Li-ion) battery capacity degradation was employed for the demonstration.

AB - Data-driven prognostics typically requires sufficient offline training data sets for accurate remaining useful life (RUL) prediction of engineering products. This paper investigates performances of typical data-driven methodologies when the amount of training data sets is insufficient. The purpose is to better understand these methodologies especially when offline training datasets are insufficient. The neural network, similarity-based approach, and copula-based sampling approach were investigated when only three run-to-failure training units were available. The example of lithium-ion (Li-ion) battery capacity degradation was employed for the demonstration.

KW - Copula-based sampling approach

KW - Data-driven

KW - Neural network

KW - Prognostics

KW - Similarity-based approach

UR - http://www.scopus.com/inward/record.url?scp=84978932707&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978932707&partnerID=8YFLogxK

U2 - 10.1115/DETC201546932

DO - 10.1115/DETC201546932

M3 - Conference contribution

AN - SCOPUS:84978932707

T3 - Proceedings of the ASME Design Engineering Technical Conference

BT - 41st Design Automation Conference

PB - American Society of Mechanical Engineers (ASME)

ER -

Xi Z, Zhao X. Data driven prognostics with lack of training data sets. In 41st Design Automation Conference. American Society of Mechanical Engineers (ASME). 2015. (Proceedings of the ASME Design Engineering Technical Conference). https://doi.org/10.1115/DETC201546932