Published October 2026, Pg. 35-43

Section: Industrial process automation

UOT: 681.58:504.064

DOI: 10.37474/0365-8554/2026-10-35-43

Environmental monitoring system and gas chromatography integration in a new approach

D.G. Xurshudov - Azerbaijan University of Architecture and Construction

Prompt assessment of indoor air quality in smart buildings is one of the essential conditions for ensuring human health, safety, and comfort. This paper proposes a new monitoring and adaptive control approach based on the integration of gas chromatography, the Internet of Things (IoT), and artificial intelligence (AI) technologies for detecting volatile organic compounds (VOCs) and other harmful gas components. Within the system, chromatogram signals obtained from the gas chromatograph undergo preprocessing to determine peak retention times, amplitudes, areas, widths, and statistical parameters. The extracted features are then transmitted to the AI module, where the identification of gas components, estimation of their concentrations, and determination of hazard levels are carried out. Operative measurements such as temperature, humidity, CO₂, CO, and others incoming from the IoT-based sensor network are fused with the chromatographic data. A simulation model of the proposed approach was developed in the MATLAB environment, establishing synthetic chromatogram generation, peak detection, gas classification, and an HVAC control mechanism based on a risk index. The proposed system can be utilized for more selective monitoring and adaptive management of air quality in smart buildings.

References:

1. Horvat T., Pehnec G., Jakovljević I. Volatile Organic Compounds in Indoor Air: Sampling, Determination, Sources, Health Risk, and Regulatory Insights. Toxics, 2025, vol. 13, No. 5, Article 344. DOI: 10.3390/toxics13050344.

2. Lee Y., Son H., Lee J., Lim S.-H. Review on micro-gas chromatography system for analysis of multiple low-concentration volatile organic compounds: preconcentration, separation, detection, integration, and challenges. Micro and Nano Systems Letters, 2024, Vol. 12, Article 11. DOI: 10.1186/s40486-024-00203-3.

3. Yashayish ve qeyri-yashayish binalarinda iqlimin tenzimlenmesi // “Inshaatda informasiya texnoloqiyalari ve sistemlerinin tetbiqi imkanlari ve perspektivleri” movzusunda Beynelxalq elmi-praktiki konfransin materiallari. – Baki, 2018, s. 240-245.

4. Bachelier F., Mascles M., McGillen M.R. et al. Development, optimization and validation of automated volatile organic compound data analysis using an on-line thermal desorption gas chromatograph with dual detection and application to measurements in ambient air // Journal of Chromatography A, 2024, vol. 1735, Article 465327. DOI: 10.1016/j.chroma.2024.465327.

5. Gaida M., Stefanuto P.H., Focant J.F. Theoretical modeling and machine learning-based data processing workflows in comprehensive two-dimensional gas chromatography – A review // Journal of Chromatography A, 2023, vol. 1711, Article 464467. DOI: 10.1016/j.chroma.2023.464467.

6. Chowdhury M.A.Z., Oehlschlaeger M.A. Artificial Intelligence in Gas Sensing: A Review. ACS Sensors, 2025, vol. 10, No. 3, pp. 1538-1563. DOI: 10.1021/acssensors.4c02272.

7. Luo W., Hu J., Hou H., Yang J. Automatic and precise identification of volatile organic compounds from gas chromatography in prolonged atmospheric monitoring // Journal of Chromatography A, 2025, vol. 1754, Article 466035. DOI: 10.1016/j.chroma.2025.466035.

8. Kapustin V.M. Intellektualʹnyye zdaniya i avtomatizatsiya tekhnoloqicheskikh protsessov. – M.: Stroyizdat, 2020, 320 s.

9. CIBSE. Guide H: Building Control Systems. London: Chartered Institution of Building Services Engineers, 2020, 154 p.

10. Fang X., Zha C., Fang W. Rapid classification and concentration prediction of VOC gaseous mixtures using sensor array with multitask learning combined with Gated Recurrent Unit (GRU) // IEEE Sensors Journal, 2025, vol. 25, No. 7, pp. 12422-12429.