Data-Driven Energy Efficiency Improvement in Industry 4.0

abstrakt

angličtina

Improving energy efficiency is one of the most important efforts towardssustainable development. Energy consumption is continuously increasing and renewable energy sources still have small contribution in energy production compared to primary sources. Energy saving measures are therefore required. These typically consist of decreasing energy consumption of buildings by insulation and replacing inefficient devices with efficient ones. The other opportunity how to improve energy efficiency is based on process data. Data-driven models for industrial energy efficiency improvement heavily rely on sensor data, experimentation data and knowledge-based data. This work reveals that too much research attention was invested into making data-driven models compared to ensuring the quality of industrial data. Furthermore, the real challenge within the industry is with data communication and infrastructure problems and not with a quality of modelling techniques. Costs related to transition from traditional industry towards Industry 4.0 are very high and especially small and medium enterprises need introduction of cheap technologies. Typically, 2 years pay-back period is acceptable, rarely 5 years, which is currently difficult to achieve. It is but a matter of time that the industry will transition towards the “digital twin”-based approach. However, the sooner the effort will be adequately distributed between challenging issues the sooner the transition happens. Global government efforts and policies are already inclining towards better industrial energy efficiencies and energy savings. This indicates a promising future for the development of a "digital twin"-based energy efficiency improving system in the industry. This approach has been successfully tested in a petrochemical case study. This approach has been successfully tested in an Oil&Gas case study. Foreseeing some potential challenges, this contribution also discusses the importance of symbiosis between researchers and industrialist to transition from traditional industry towards Industry 4.0. The authors estimate that well-developed artificial intelligence based infrastructure available to wide range of enterprises will be ready not sooner than in 2040.

Data-Driven; Energy Efficiency; Improvement

TOUŠ, M.; MÁŠA, V.; TENG, S.; KORČEK, L.

26. 8. 2020

Volos

2653-8911

Book of Abstracts of the Energy, Sustainability and Climate Change Conference

7

1

Řecká republika

30

30

1

http://escc.uth.gr/wp-content/uploads/2020/11/ESCC-2020_Book-of-Abstracts.pdf