Details
| Original language | English |
|---|---|
| Title of host publication | GECCO 2021 - Proceedings of the 2021 Genetic and Evolutionary Computation Conference |
| Pages | 368-376 |
| Number of pages | 9 |
| ISBN (electronic) | 9781450383509 |
| Publication status | Published - 26 Jun 2021 |
| Externally published | Yes |
| Event | 2021 Genetic and Evolutionary Computation Conference, GECCO 2021 - Virtual, Online, France Duration: 10 Jul 2021 → 14 Jul 2021 |
Publication series
| Name | ACM Conferences |
|---|
Abstract
Automated machine learning (AutoML) strives for automatically constructing and configuring compositions of machine learning algorithms, called pipelines, with the goal to optimize a suitable performance measure on a concrete learning task. So far, most AutoML tools are focused on standard problem classes, such as classification and regression. In the field of predictive maintenance, especially the estimation of remaining useful lifetime (RUL), the task of AutoML becomes more complex. In particular, a good feature representation for multivariate sensor data is essential to achieve good performance. Due to the need for methods generating feature representations, the search space of candidate pipelines enlarges. Moreover, the runtime of a single pipeline increases substantially. In this paper, we tackle these problems by partitioning the search space into two sub-spaces, one for feature extraction methods and one for regression methods, and employ cooperative coevolution for searching a good combination. Thereby, we benefit from the fact that the generated feature representations can be cached, whence the evaluation of multiple regressors based on the same feature representation speeds up, allowing the evaluation of more candidate pipelines. Experimentally, we show that our coevolutionary strategy performs superior to the baselines.
Keywords
- AutoML, Coevolution, Predictive maintenance, Remaining useful lifetime
ASJC Scopus subject areas
- Mathematics(all)
- Computational Mathematics
- Biochemistry, Genetics and Molecular Biology(all)
- Genetics
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
GECCO 2021 - Proceedings of the 2021 Genetic and Evolutionary Computation Conference. 2021. p. 368-376 (ACM Conferences).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Coevolution of remaining useful lifetime estimation pipelines for automated predictive maintenance
AU - Tornede, Tanja
AU - Tornede, Alexander
AU - Wever, Marcel
AU - Hüllermeier, Eyke
N1 - Publisher Copyright: © 2021 ACM.
PY - 2021/6/26
Y1 - 2021/6/26
N2 - Automated machine learning (AutoML) strives for automatically constructing and configuring compositions of machine learning algorithms, called pipelines, with the goal to optimize a suitable performance measure on a concrete learning task. So far, most AutoML tools are focused on standard problem classes, such as classification and regression. In the field of predictive maintenance, especially the estimation of remaining useful lifetime (RUL), the task of AutoML becomes more complex. In particular, a good feature representation for multivariate sensor data is essential to achieve good performance. Due to the need for methods generating feature representations, the search space of candidate pipelines enlarges. Moreover, the runtime of a single pipeline increases substantially. In this paper, we tackle these problems by partitioning the search space into two sub-spaces, one for feature extraction methods and one for regression methods, and employ cooperative coevolution for searching a good combination. Thereby, we benefit from the fact that the generated feature representations can be cached, whence the evaluation of multiple regressors based on the same feature representation speeds up, allowing the evaluation of more candidate pipelines. Experimentally, we show that our coevolutionary strategy performs superior to the baselines.
AB - Automated machine learning (AutoML) strives for automatically constructing and configuring compositions of machine learning algorithms, called pipelines, with the goal to optimize a suitable performance measure on a concrete learning task. So far, most AutoML tools are focused on standard problem classes, such as classification and regression. In the field of predictive maintenance, especially the estimation of remaining useful lifetime (RUL), the task of AutoML becomes more complex. In particular, a good feature representation for multivariate sensor data is essential to achieve good performance. Due to the need for methods generating feature representations, the search space of candidate pipelines enlarges. Moreover, the runtime of a single pipeline increases substantially. In this paper, we tackle these problems by partitioning the search space into two sub-spaces, one for feature extraction methods and one for regression methods, and employ cooperative coevolution for searching a good combination. Thereby, we benefit from the fact that the generated feature representations can be cached, whence the evaluation of multiple regressors based on the same feature representation speeds up, allowing the evaluation of more candidate pipelines. Experimentally, we show that our coevolutionary strategy performs superior to the baselines.
KW - AutoML
KW - Coevolution
KW - Predictive maintenance
KW - Remaining useful lifetime
UR - http://www.scopus.com/inward/record.url?scp=85110197221&partnerID=8YFLogxK
U2 - 10.1145/3449639.3459395
DO - 10.1145/3449639.3459395
M3 - Conference contribution
AN - SCOPUS:85110197221
SN - 978-145038350-9
T3 - ACM Conferences
SP - 368
EP - 376
BT - GECCO 2021 - Proceedings of the 2021 Genetic and Evolutionary Computation Conference
T2 - 2021 Genetic and Evolutionary Computation Conference, GECCO 2021
Y2 - 10 July 2021 through 14 July 2021
ER -