Qualitative identification of single/mixture gases based on Fe-ZnO sensor array and PSO-BP neural network

• Published in: IEEE sensors journal Vol. 23; no. 17; p. 1
• Main Authors: Li, Meihua, Ge, Shikun, Gu, Yunlong, Zhang, Yunfan, Li, Xiao, Zhu, Huichao, Wei, Guangfen
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Back propagation networks; concentration level analysis; Gas detectors; II-VI semiconductor materials; Iron; particle swarm algorithm; Particle swarm optimization; Photoelectrons; qualitative identification; self-assembled rod-flower structure; Self-assembly; sensor array; Sensor arrays; Sensors; Swarm intelligence; Temperature sensors; X ray photoelectron spectroscopy; Zinc; Zinc oxide
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2023.3296724

Fe-ZnO materials with self-assembled rod-flower structure were synthesized. XRD, EDS, SEM and XPS were used to characterize the morphology, elemental composition and valence analysis of Fe-ZnO. It was verified that Fe-ZnO sensors have good performances for single/mixed test gases. Combining the sensor array with a back propagation neural network algorithm optimized by particle swarm (PSO-BPNN), qualitative identification of 10 different gas concentration levels under 3 categories was achieved with a detection accuracy of 95%. High classification detection was achieved using the PSO-BPNN model even under the influence of different humidity levels (RH = 35%, 50%, 80%). So, the combined Fe-ZnO sensor array with PSO-BPNN model can effectively detect toxic gases at different concentration level and therefore has some potential practical value.