Machine learning based internal and external energy assessment of automotive factories

Dominik Flick; Melina  Vruna; Milan  Bartos; Li  Ji; Christoph Herrmann; Sebastian Thiede

doi:10.1016/j.cirp.2023.04.038

Machine learning based internal and external energy assessment of automotive factories

Dominik Flick, Melina Vruna, Milan Bartos, Li Ji, Christoph Herrmann, Sebastian Thiede^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

1 Citation (Scopus)

66 Downloads (Pure)

Abstract

In order to reduce industrial greenhouse gas emissions, systematic energy demand analysis and the derivation of improvement strategies are key. Against this background, a methodology for data driven energy demand prediction and performance benchmarking for factories is presented. The machine learning based approach enables to quantify performance influencing factors, identify “best in class” factories and fields of action for improvement. The results are validated within an automotive OEM internal and even external competitor assessment. The transferable approach based on well accessible public data also enables larger industry wide studies.

Original language	English
Pages (from-to)	21-24
Number of pages	4
Journal	CIRP annals : manufacturing technology
Volume	72
Issue number	1
Early online date	2 Jun 2023
DOIs	https://doi.org/10.1016/j.cirp.2023.04.038
Publication status	Published - 13 Jul 2023

Keywords

Energy efficiency
Factory
Machine learning
UT-Hybrid-D

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.cirp.2023.04.038Licence: CC BY

1-s2.0-S0007850623000781-mainFinal published version, 993 KBLicence: CC BY

Cite this

@article{1aa743ebe440412dbd219440d4ef6e9d,

title = "Machine learning based internal and external energy assessment of automotive factories",

abstract = "In order to reduce industrial greenhouse gas emissions, systematic energy demand analysis and the derivation of improvement strategies are key. Against this background, a methodology for data driven energy demand prediction and performance benchmarking for factories is presented. The machine learning based approach enables to quantify performance influencing factors, identify “best in class” factories and fields of action for improvement. The results are validated within an automotive OEM internal and even external competitor assessment. The transferable approach based on well accessible public data also enables larger industry wide studies.",

keywords = "Energy efficiency, Factory, Machine learning, UT-Hybrid-D",

author = "Dominik Flick and Melina Vruna and Milan Bartos and Li Ji and Christoph Herrmann and Sebastian Thiede",

year = "2023",

month = jul,

day = "13",

doi = "10.1016/j.cirp.2023.04.038",

language = "English",

volume = "72",

pages = "21--24",

journal = "CIRP annals : manufacturing technology",

issn = "0007-8506",

publisher = "Elsevier",

number = "1",

}

TY - JOUR

T1 - Machine learning based internal and external energy assessment of automotive factories

AU - Flick, Dominik

AU - Vruna, Melina

AU - Bartos, Milan

AU - Ji, Li

AU - Herrmann, Christoph

AU - Thiede, Sebastian

PY - 2023/7/13

Y1 - 2023/7/13

N2 - In order to reduce industrial greenhouse gas emissions, systematic energy demand analysis and the derivation of improvement strategies are key. Against this background, a methodology for data driven energy demand prediction and performance benchmarking for factories is presented. The machine learning based approach enables to quantify performance influencing factors, identify “best in class” factories and fields of action for improvement. The results are validated within an automotive OEM internal and even external competitor assessment. The transferable approach based on well accessible public data also enables larger industry wide studies.

AB - In order to reduce industrial greenhouse gas emissions, systematic energy demand analysis and the derivation of improvement strategies are key. Against this background, a methodology for data driven energy demand prediction and performance benchmarking for factories is presented. The machine learning based approach enables to quantify performance influencing factors, identify “best in class” factories and fields of action for improvement. The results are validated within an automotive OEM internal and even external competitor assessment. The transferable approach based on well accessible public data also enables larger industry wide studies.

KW - Energy efficiency

KW - Factory

KW - Machine learning

KW - UT-Hybrid-D

U2 - 10.1016/j.cirp.2023.04.038

DO - 10.1016/j.cirp.2023.04.038

M3 - Article

SN - 0007-8506

VL - 72

SP - 21

EP - 24

JO - CIRP annals : manufacturing technology

JF - CIRP annals : manufacturing technology

IS - 1

ER -

Machine learning based internal and external energy assessment of automotive factories

Abstract

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this