Publication detail

Virtual Reality in Context of Industry 4.0

KOVÁŘ, J. MOURALOVÁ, K. KŠICA, F. KROUPA, J. ANDRŠ, O. HADAŠ, Z.

Original Title

Virtual Reality in Context of Industry 4.0

Czech Title

Virtual Reality in Context of Industry 4.0

English Title

Virtual Reality in Context of Industry 4.0

Type

conference paper

Language

en

Original Abstract

In industrial environments, it is often difficult and expensive to collect a good amount of data to adequately train expert systems for regression purposes. Therefore the usage of already available data, related to environments showing similar characteristics, could represent an effective approach to find a good balance between regression performance and the amount of data to gather for training. In this paper, the authors propose two alternative strategies for improving the regression performance by using heterogeneous data, i.e. data coming from diverse environments with respect to the one taken as reference for testing. These strategies are based on a standard machine learning algorithm, i.e. the Artificial Neural Network (ANN). The employed data came from measurements in industrial plants for energy production through the combustion of coal powder. The powder is transported in air within ducts and its size is detected by means of Acoustic Emissions (AE) produced by the impact of powder on the inner surface of the duct. The estimation of powder size distribution from AE signals is the task addressed in this work. Computer simulations show how the proposed strategies achieve a relevant improvement of regression performance with respect to the standard approach, using ANN directly on the dataset related to the reference plant.

Czech abstract

V průmyslovém prostředí, je často obtížné a drahé nasbírat odpovídající množství dat, pro expertní systémy pro regresní účely. Proto použití již dostupných údajů, týkajících se prostředí, které zobrazují podobné charakteristiky, může představovat efektivní přístup k nalezení dobrého poměru mezi výkonem a regresním množstvím shromažěných dat. V tomto článku jsou navrženy dvě alternativní strategie pro zlepšení regresních výstupů použitím heterogenních dat, tj data přicházející z různorodých prostředí s ohledem na jednu referenci pro testování.

English abstract

In industrial environments, it is often difficult and expensive to collect a good amount of data to adequately train expert systems for regression purposes. Therefore the usage of already available data, related to environments showing similar characteristics, could represent an effective approach to find a good balance between regression performance and the amount of data to gather for training. In this paper, the authors propose two alternative strategies for improving the regression performance by using heterogeneous data, i.e. data coming from diverse environments with respect to the one taken as reference for testing. These strategies are based on a standard machine learning algorithm, i.e. the Artificial Neural Network (ANN). The employed data came from measurements in industrial plants for energy production through the combustion of coal powder. The powder is transported in air within ducts and its size is detected by means of Acoustic Emissions (AE) produced by the impact of powder on the inner surface of the duct. The estimation of powder size distribution from AE signals is the task addressed in this work. Computer simulations show how the proposed strategies achieve a relevant improvement of regression performance with respect to the standard approach, using ANN directly on the dataset related to the reference plant.

Keywords

Virtual Reality; Industry 4.0; Factory of Future; Dynamics; FEM; Atomic Force Microscopy; Microstructures

Released

07.12.2016

Publisher

Czech Technical University in Prague, Faculty of Electrical Engineering

Location

Praha

ISBN

978-80-01-05882-4

Book

Mechatronika 2016

Pages from

1

Pages to

7

Pages count

8

URL

BibTex


@inproceedings{BUT131170,
  author="Jiří {Kovář} and Kateřina {Mouralová} and Filip {Kšica} and Jiří {Kroupa} and Ondřej {Andrš} and Zdeněk {Hadaš}",
  title="Virtual Reality in Context of Industry 4.0",
  annote="In industrial environments, it is often difficult and
expensive to collect a good amount of data to adequately train
expert systems for regression purposes. Therefore the usage of
already available data, related to environments showing similar
characteristics, could represent an effective approach to find a
good balance between regression performance and the amount of
data to gather for training. In this paper, the authors propose two
alternative strategies for improving the regression performance by
using heterogeneous data, i.e. data coming from diverse
environments with respect to the one taken as reference for testing.
These strategies are based on a standard machine learning
algorithm, i.e. the Artificial Neural Network (ANN). The employed
data came from measurements in industrial plants for energy
production through the combustion of coal powder. The powder is
transported in air within ducts and its size is detected by means of
Acoustic Emissions (AE) produced by the impact of powder on the
inner surface of the duct. The estimation of powder size
distribution from AE signals is the task addressed in this work.
Computer simulations show how the proposed strategies achieve a
relevant improvement of regression performance with respect to
the standard approach, using ANN directly on the dataset related
to the reference plant.",
  address="Czech Technical University in Prague, Faculty of Electrical Engineering",
  booktitle="Mechatronika 2016",
  chapter="131170",
  howpublished="electronic, physical medium",
  institution="Czech Technical University in Prague, Faculty of Electrical Engineering",
  year="2016",
  month="december",
  pages="1--7",
  publisher="Czech Technical University in Prague, Faculty of Electrical Engineering",
  type="conference paper"
}