Publication type: Conference poster
Type of review: Peer review (publication)
Title: Implementation of multi-task learning neural network architectures for robust industrial optical sensing
Authors: Venturini, Francesca
Michelucci, Umberto
Baumgartner, Michael
et. al: No
DOI: 10.1117/12.2593469
Proceedings: Optical Measurement Systems for Industrial Inspection XII
Editors of the parent work: Lehmann, Peter
Osten, Wolfgang
Albertazzi Gonçalves Jr., Armandi
Conference details: SPIE Optical Metrology, online, 21-25 June 2021
Issue Date: Jun-2021
Series: Proceedings of SPIE
Series volume: 11782
Publisher / Ed. Institution: Society of Photo-Optical Instrumentation Engineers
Publisher / Ed. Institution: Bellingham
ISBN: 9781510643987
9781510643994
ISSN: 0277-786X
1996-756X
Language: English
Subjects: Oxygen monitoring; Luminescence quenching; Artificial neural networks
Subject (DDC): 006: Special computer methods
620: Engineering
Abstract: The simultaneous determination of multiple physical or chemical parameters can be very advantageous in many sensor applications. In some cases, it is unavoidable because the parameters of interest display cross sensitivities or depend on multiple quantities varying simultaneously. One notable example is the determination of oxygen partial pressure via luminescence quenching. The measuring principle is based on the measurement of the luminescence of a specific molecule, whose intensity and decay time are reduced due to collisions with oxygen molecules. Since both the luminescence and the quenching phenomena are strongly temperature-dependent, this type of sensor needs continuous monitoring of the temperature. This is typically achieved by adding temperature sensors and employing a multi-parametric model (Stern{Volmer equation), whose parameters are all temperature-dependent. As a result, the incorrect measurement of the temperature of the indicator is a major source of error. In this work a new approach based on multi-task learning (MTL) artificial neural networks (ANN) was successfully implemented to achieve robust sensing for industrial applications. These were integrated in a sensor that not only does not need the separate detection of temperature but even exploits the intrinsic cross-interferences of the sensing principle to predict simultaneously oxygen partial pressure and temperature. A detailed analysis of the robustness of the method was performed to demonstrate its potential for industrial applications. This type of sensor could in the future signi ficantly simplify the design of the sensor and at the same time increase its performance.
URI: https://digitalcollection.zhaw.ch/handle/11475/23062
Fulltext version: Published version
License (according to publishing contract): Licence according to publishing contract
Departement: School of Engineering
Organisational Unit: Institute of Applied Mathematics and Physics (IAMP)
Appears in collections:Publikationen School of Engineering

Files in This Item:
There are no files associated with this item.
Show full item record
Venturini, F., Michelucci, U., & Baumgartner, M. (2021). Implementation of multi-task learning neural network architectures for robust industrial optical sensing [Conference poster]. In P. Lehmann, W. Osten, & A. Albertazzi Gonçalves Jr. (Eds.), Optical Measurement Systems for Industrial Inspection XII. Society of Photo-Optical Instrumentation Engineers. https://doi.org/10.1117/12.2593469
Venturini, F., Michelucci, U. and Baumgartner, M. (2021) ‘Implementation of multi-task learning neural network architectures for robust industrial optical sensing’, in P. Lehmann, W. Osten, and A. Albertazzi Gonçalves Jr. (eds) Optical Measurement Systems for Industrial Inspection XII. Bellingham: Society of Photo-Optical Instrumentation Engineers. Available at: https://doi.org/10.1117/12.2593469.
F. Venturini, U. Michelucci, and M. Baumgartner, “Implementation of multi-task learning neural network architectures for robust industrial optical sensing,” in Optical Measurement Systems for Industrial Inspection XII, Jun. 2021. doi: 10.1117/12.2593469.
VENTURINI, Francesca, Umberto MICHELUCCI und Michael BAUMGARTNER, 2021. Implementation of multi-task learning neural network architectures for robust industrial optical sensing. In: Peter LEHMANN, Wolfgang OSTEN und Armandi ALBERTAZZI GONÇALVES JR. (Hrsg.), Optical Measurement Systems for Industrial Inspection XII. Conference poster. Bellingham: Society of Photo-Optical Instrumentation Engineers. Juni 2021. ISBN 9781510643987
Venturini, Francesca, Umberto Michelucci, and Michael Baumgartner. 2021. “Implementation of Multi-Task Learning Neural Network Architectures for Robust Industrial Optical Sensing.” Conference poster. In Optical Measurement Systems for Industrial Inspection XII, edited by Peter Lehmann, Wolfgang Osten, and Armandi Albertazzi Gonçalves Jr. Bellingham: Society of Photo-Optical Instrumentation Engineers. https://doi.org/10.1117/12.2593469.
Venturini, Francesca, et al. “Implementation of Multi-Task Learning Neural Network Architectures for Robust Industrial Optical Sensing.” Optical Measurement Systems for Industrial Inspection XII, edited by Peter Lehmann et al., Society of Photo-Optical Instrumentation Engineers, 2021, https://doi.org/10.1117/12.2593469.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.