Self-verifying time-resolved multicomponent gas analysis from raw sensor signals
Abstract
Gas sensor arrays can estimate the composition of gas mixtures from their response patterns. However, when a sensor is used outside the laboratory, the true gas concentrations are unknown, so there is usually no direct way to determine whether the estimated result is reliable. Here, we develop a physics-constrained neural network that estimates time-varying gas concentrations and reconstructs the corresponding sensor signals at the same time. We tested the method with a twelve-channel membrane-type surface stress sensor array exposed to water-ethanol mixtures whose concentrations changed over time. The model reconstructed the concentration profiles of both components from the raw signals. Artificial offsets and sensitivity changes in one channel were detected from disagreement between the measured and reconstructed signals. Deletion or replacement of part of a measurement record was detected from violations of the sorption and mechanical equations. This approach enables time-resolved multicomponent gas analysis with self-verification from a single measurement.
Related
- Trainable, self-verifying variational quantum eigensolver using adiabatic warm starts
- AeroProp-X: An Open-Source, Self-Verifying Method-of-Characteristics Toolkit for Edge-Capable Rocket Nozzle Design and Aerothermodynamic Analysis
- Modulating the polarization-resolved second harmonic generation response of a Sulfamic acid multicomponent crystal via amino acid coformer selection
- Profiling a Rydberg-Atom Electric Field Sensor for Off-Resonant Detection of Sub-100 MHz RF Signals
- Combining physical models with dynamically acquired experimental information for the optimization of multicomponent NASICON fast ionic conductors in a self-driving laboratory
BibTeX
@misc{zhou2026selfverifying,
title = {{Self-verifying time-resolved multicomponent gas analysis from raw sensor signals}},
author = {YingCheng Zhou and Kosuke Minami and Genki Yoshikawa},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.38663},
eprint = {2609.38663},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.38663},
}
RIS
TY - UNPB
TI - Self-verifying time-resolved multicomponent gas analysis from raw sensor signals
AU - YingCheng Zhou
AU - Kosuke Minami
AU - Genki Yoshikawa
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.38663
UR - https://arxiv.org/abs/2609.38663
AB - Gas sensor arrays can estimate the composition of gas mixtures from their response patterns. However, when a sensor is used outside the laboratory, the true gas concentrations are unknown, so there is usually no direct way to determine whether the estimated result is reliable. Here, we develop a physics-constrained neural network that estimates time-varying gas concentrations and reconstructs the corresponding sensor signals at the same time. We tested the method with a twelve-channel membrane-type surface stress sensor array exposed to water-ethanol mixtures whose concentrations changed over time. The model reconstructed the concentration profiles of both components from the raw signals. Artificial offsets and sensitivity changes in one channel were detected from disagreement between the measured and reconstructed signals. Deletion or replacement of part of a measurement record was detected from violations of the sorption and mechanical equations. This approach enables time-resolved multicomponent gas analysis with self-verification from a single measurement.
ER -