Uncertainty-aware Bayesian neural networks for FTIR gas-phase process monitoring: a semi-synthetic feasibility study
at - Automatisierungstechnik · 26.10.2026 · 74 (10) · 818-831
DOI: 10.1515/auto-2026-0033 ↗Kurz gefasst
Fachartikel in der Zeitschrift at - Automatisierungstechnik, online erschienen am 09.11.2026. Verfasst von André Orth und 2 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
To remain safe and actionable, multi-component gas-phase Fourier-transform infrared (FTIR) process analysis requires a reliability estimate for each concentration prediction. In a semi-synthetic feasibility study for a fixed compound library, we present a Bayesian one-dimensional Convolutional Neural Network (1D-CNN) trained on spectra from single-compound reference data that predicts concentrations, compound presence probabilities and per-prediction uncertainty bounds. The model yields accurate concentration predictions (mean absolute error 0.165 in log 10 -space, within a factor of about 1.5) and uncertainty bounds that remain well-calibrated under severe instrumental artifacts. A pre-inference amplitude guard screens for inputs outside the detector’s valid operating range. Validation on measured spectra is the necessary next step before deployment.
Zitieren
APA
Orth, A., Höfer, H. H., & Reischl, M. (2026). Uncertainty-aware Bayesian neural networks for FTIR gas-phase process monitoring: a semi-synthetic feasibility study. at - Automatisierungstechnik, 74(10), 818-831. https://doi.org/10.1515/auto-2026-0033
Vancouver
Orth A, Höfer HH, Reischl M. Uncertainty-aware Bayesian neural networks for FTIR gas-phase process monitoring: a semi-synthetic feasibility study. at - Automatisierungstechnik. 2026;74(10):818-831. doi:10.1515/auto-2026-0033
BibTeX
@article{Orth2026,
author = {Orth, André and Höfer, Hawo H. and Reischl, Markus},
title = {Uncertainty-aware Bayesian neural networks for FTIR gas-phase process monitoring: a semi-synthetic feasibility study},
journal = {at - Automatisierungstechnik},
year = {2026},
volume = {74},
number = {10},
pages = {818--831},
doi = {10.1515/auto-2026-0033}
}
EUVIMED