| Title: |
Linear and non-linear modelling methods for a gas sensor array developed for process control applications |
| Authors: |
Lakhmi, Riadh; Fischer, Marc; Darves-Blanc, Quentin; Alrammouz, Rouba; Rieu, Mathilde; Viricelle, Jean-Paul |
| Contributors: |
Centre Sciences des Processus Industriels et Naturels (SPIN-ENSMSE); École des Mines de Saint-Étienne (Mines Saint-Étienne MSE); Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT); Laboratoire Georges Friedel (LGF-ENSMSE); Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT)-Université de Lyon-Centre National de la Recherche Scientifique (CNRS) |
| Source: |
ISSN: 1424-8220 ; Sensors ; https://hal-emse.ccsd.cnrs.fr/emse-04611143 ; Sensors, 2024, 24 (11), pp.3499. ⟨10.3390/s24113499⟩ ; https://www.mdpi.com/1424-8220/24/11/3499. |
| Publisher Information: |
CCSD; MDPI |
| Publication Year: |
2024 |
| Collection: |
Mines de Saint-Etienne: Archives Ouvertes / Open Archive (HAL) |
| Subject Terms: |
Power to X; Multivariate analysis; PLS; ANN; Sensor array; [SPI.GPROC]Engineering Sciences [physics]/Chemical and Process Engineering |
| Description: |
International audience ; New process developments linked to Power to X (energy storage or energy conversion toanother form of energy) require tools to perform process monitoring. The main gases involved inthese types of processes are H 2 , CO, CH 4 , and CO 2 . Because of the non-selectivity of the sensors, a multi-sensor matrix has been built in this work based on commercial sensors having very different transduction principles, and, therefore, providing richer information. To treat the data provided by the sensor array and extract gas mixture composition (nature and concentration), linear ( Multi Linear Regression—Ordinary Least Square “MLR-OLS” and Multi Linear Regression—Partial Least Square “MLR-PLS”) and non-linear ( Artificial Neural Network “ANN”) models have been built. The MLR-OLS model was disqualified during the training phase since it did not show good results even in the training phase, which could not lead to effective predictions during the validation phase. Then, the performances of MLR-PLS and ANN were evaluated with validation data. Good concentrationpredictions were obtained in both cases for all the involved analytes. However, in the case of methane,better prediction performances were obtained with ANN, which is consistent with the fact that theMOX sensor’s response to CH 4 is logarithmic, whereas only linear sensor responses were obtained for the other analytes. Finally, prediction tests performed on one-year aged sensor platforms revealed that PLS model predictions on aged platforms mainly suffered from concentration offsets and thatANN predictions mainly suffered from a drop of sensitivity. |
| Document Type: |
article in journal/newspaper |
| Language: |
English |
| DOI: |
10.3390/s24113499 |
| Availability: |
https://hal-emse.ccsd.cnrs.fr/emse-04611143; https://hal-emse.ccsd.cnrs.fr/emse-04611143v1/document; https://hal-emse.ccsd.cnrs.fr/emse-04611143v1/file/RL_MF%20Sensors%202024.pdf; https://doi.org/10.3390/s24113499 |
| Rights: |
https://creativecommons.org/licenses/by/4.0/ ; info:eu-repo/semantics/OpenAccess |
| Accession Number: |
edsbas.D080E61C |
| Database: |
BASE |