Applications of Dimensionality Reduction to the Diagnosis of Energy Systems

Sylvain Lespinats, Benoit Colange and Denys Dutykh
Additional contact information
Sylvain Lespinats: Grenoble Alpes University, National Institute of Solar Energy (INES)
Benoit Colange: Grenoble Alpes University, National Institute of Solar Energy (INES)
Denys Dutykh: Université Grenoble Alpes, Université Savoie Mont Blanc, Campus Scientifique, CNRS - LAMA UMR 5127

Chapter Chapter 8 in Nonlinear Dimensionality Reduction Techniques, 2022, pp 177-192 from Springer

Abstract: Abstract This Chapter presents a few examples of applications of dimensionality reduction for the analysis of data towards the diagnosis of energy systems. These systems encompass smart-buildings (Sect. 8.1), photovoltaic systems (Sect. 8.2) and batteries (Sect. 8.3). Diagnosis aims at identifying the occurrence of faults in a system. These faults are characterized by their signatures, that is their effects on the system and the monitored variables. The discriminability between the signatures of different faults is a necessary condition for the possibility of diagnostic. In that regard, Dimensionality Reduction (DR) may allow to compare different signatures, provided for instance by I–V curves for photovoltaic systems and by Power Spectral Density of acoustic signals for Li-ion batteries.

Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-030-81026-9_8

Ordering information: This item can be ordered from
http://www.springer.com/9783030810269

DOI: 10.1007/978-3-030-81026-9_8

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().