Identification of CO2 , SO2 , and a Mixture of Both Gases Using Optical Imaging Combined with Convolutional Neural Network (CNN)
Article Sidebar
-
CNN, CO2 , SO2 , Optical Imaging , Infrared Camera
Abstract
CO2 and SO2 gases are utilized in various industrial applications and are subjects of environmental research. However, these gases are considered toxic and pose dangers at certain concentrations. Therefore, it is crucial to monitor and control the exposure to these gases in the environment to prevent reaching hazardous levels that could endanger both humans and the environment. A non-contact detection and monitoring system is essential to minimize the adverse effects of direct gas exposure. In this research, a non-contact detection system for CO2, SO2, and mixed gases was developed using optical imaging analysis generated by infrared cameras. The images were captured using the FLIR Vue Pro-R infrared camera, with infrared absorbing gas sourced from a 50-watt tungsten lamp. Visual identification of these gases through optical imaging is challenging; however, this study successfully identified these gases using a Convolutional Neural Network (CNN). The CNN architecture used in this study is DenseNet (Densely Connected Convolutional Networks), comprising 169 convolution layers. The CNN model was trained and tested on experimental optical imaging data, categorized into three classes: CO2, SO2, and a mixture of gases. A total of 1030 optical imaging data points were utilized for training. Training was conducted using the AdamW optimization function over 28 epochs. The evaluation of results yielded accuracy, precision, recall, and F1-score metrics. The novelty of this study lies in the successful identification of CO2, SO2, and their mixture by the CNN model with an accuracy of 85%. Precision, recall, and F1-score values are all 0.85. These results indicate that the CNN model effectively distinguishes optical imaging of each gas (CO2, SO2, and their mixture) consistently and accurately. Consequently, it can be concluded that the CNN model performs well in distinguishing between these gases in optical imaging analysis.
References
Battalwar, P., J. Gokhale, and U. Bansod (2015). Infrared Thermography and IR Camera. International Journal of Research in Science & Engineering, 1(3); 9–14
Chu, J., W. Li, X. Yang, Y. Wu, D. Wang, A. Yang, H. Yuan, X. Wang, Y. Li, and M. Rong (2021). Identification of Gas Mixtures Via Sensor Array Combining with Neural Networks. Sensors and Actuators B: Chemical, 329; 129090
Cronin, S. J., G. Lube, D. S. Dayudi, S. Sumarti, and S. Subrandiyo (2013). Insights into the October November 2010 Gunung Merapi Eruption (central Java, Indonesia) from the Stratigraphy, Volume and Characteristics of Its Pyroclastic Deposits. Journal of Volcanology and Geothermal Research, 261; 244–259
Da Wang, Y., M. J. Blunt, R. T. Armstrong, and P. Mostaghimi (2021). Deep Learning in Pore Scale Imaging and Modeling. Earth-Science Reviews, 215; 103555
Di Traglia, F., T. Nolesini, L. Solari, A. Ciampalini, W. Frodella, D. Steri, B. Allotta, A. Rindi, L. Marini, and N. Monni (2018). Lava Delta Deformation As a Proxy for Submarine Slope Instability. Earth and Planetary Science Letters, 488; 46–58
Fiorentino, M. C., F. P. Villani, M. Di Cosmo, E. Frontoni, and S. Moccia (2023). A Review on Deep-Learning Algorithms for Fetal Ultrasound-Image Analysis. Medical Image Analysis, 83; 102629
Frei, M. and F. E. Kruis (2021). Fiber-Cnn: Expanding Mask R-CNN to Improve Image-Based Fiber Analysis. Powder Technology, 377; 974–991
He, H., H. Xu, Y. Zhang, K. Gao, H. Li, L. Ma, and J. Li (2022). Mask R-CNN Based Automated Identification and Extraction of Oil Well Sites. International Journal of Applied Earth Observation and Geoinformation, 112; 102875
Humaida, H. (2005). A Study on Carbon Isotope of CO2 and CH4 in Western Dieng Plateu by Gas Chromatography-Isotope Ratio Mass Spectrometer (GC-IRMS). Indonesian Journal of Chemistry, 5(1); 11–14
Jeffery, A. J., R. Gertisser, V. R. Troll, E. M. Jolis, B. Dahren, C. Harris, A. G. Tindle, K. Preece, B. O’Driscoll, and H. Humaida (2013). The Pre-Eruptive Magma Plumbing System of the 2007-2008 Dome-Forming Eruption of Kelut Volcano, East Java, Indonesia. Contributions to Mineralogy and Petrology, 166; 275–308
Jousset, P., J. Pallister, M. Boichu, M. F. Buongiorno, A. Budisantoso, F. Costa, S. Andreastuti, F. Prata, D. Schneider, and L. Clarisse (2012). The 2010 Explosive Eruption of Java’s Merapi Volcano-A ‘100-Year’event. Journal of Volcanology and Geothermal Research, 241; 121–135
Malamousi, K., K. Delibasis, B. Allcock, and S. Kamnis (2022). Digital Transformation of Thermal and Cold Spray Processes with Emphasis on Machine Learning. Surface and Coatings Technology, 433; 128138
Nie, F., H. Wang, Q. Song, Y. Zhao, J. Shen, and M. Gong (2022). Image Identification for Two Phase Flow Patterns Based on CNN Algorithms. International Journal of Multiphase Flow, 152; 104067
Notsu, K., T. Mori, S. C. D. Vale, H. Kagi, and T. Ito (2006). Monitoring Quiescent Volcanoes by Diffuse CO2 Degassing: Case Study of Mt. Fuji, Japan. Pure and Applied Geophysics, 163; 825–835
Parmar, V., N. Bhatia, S. Negi, and M. Suri (2020). Exploration of Optimized Semantic Segmentation Architectures for Edge-Deployment on Drones. http://arxiv.org/abs/2007.02839
Paul, E. and R. Sabeenian (2022). Modified Convolutional Neural Network with Pseudo-CNN for Removing Nonlinear Noise in Digital Images. Displays, 74; 102258
Peng, P., X. Zhao, X. Pan, and W. Ye (2018). Gas Classification Using Deep Convolutional Neural Networks. Sensors, 18(1); 157
Salamah, U., S. Sakti, H. Soetedjo, and A. Naba (2022). Non-Contact Technique for CO2 Gas Monitoring Using Thermal Imaging Camera. In Journal of Physics: Conference Series, volume 2165. IOP Publishing, page 012019
Salamah, U., S. P. Sakti, H. Soetedjo, and A. Naba (2023). Optical Imaging Identification of CO2 and SO2 in Non-Contact Detection System Using Infrared Camera. In AIP Conference Proceedings, volume 2619. AIP Publishing, page 050014
Takle, E. (2015). Agricultural Meteorology and Climatology. Elsevier, pages 92–97
Tang, P., D. Zhang, and H. Li (2022). Predicting Permeability from 3D Rock Images Based on CNN with Physical Information. Journal of Hydrology, 606; 127473
Vollmer, M. and K.-P. Möllmann (2011). 3.2-IR Imaging of CO2: Basics, Experiments, and Potential Industrial Applications. Proceedings IRS2 2011; 59–64
Wei, G., G. Li, J. Zhao, and A. He (2019). Development of a LeNet-5 Gas Identification CNN Structure for Electronic Noses. Sensors, 19(1); 217
Wu, Y., R. Du, J. Feng, S. Qi, H. Pang, S. Xia, and W. Qian (2023). Deep CNN for COPD Identification by Multi-View Snapshot Integration of 3D Airway Tree and Lung Field. Biomedical Signal Processing and Control, 79; 104162
Xiao, P., J. Zhang, P. Webley, G. Li, R. Singh, and R. Todd (2008). Capture of CO2 from Flue Gas Streams with Zeolite 13X by Vacuum-Pressure Swing Adsorption. Adsorption, 14; 575–582
Xiong, L., M. He, C. Hu, Y. Hou, S. Han, and X. Tang (2023). Image Presentation and Effective Classification of Odor Intensity Levels Using Multi-Channel Electronic Nose Technology Combined with Gasf and CNN. Sensors and Actuators B: Chemical, 395; 134492
Yacouby, R. and D. Axman (2020). Probabilistic Extension of Precision, Recall, and F1 Score for More Thorough Evaluation of Classification Models. In Proceedings of the First Workshop on Evaluation and Comparison of Nlp Systems. pages 79–91
Yang, Z., H. Ji, Z. Huang, B. Wang, and H. Li (2017). Application of Convolution Neural Network to Flow Pattern Identification of Gas-Liquid Two-Phase Flow in Small-Size Pipe. In 2017 Chinese Automation Congress (CAC). IEEE, pages 1389–1393
Zeng, J., H. Wu, and M. He (2023). Image Classification Combined with Faster R-CNN for the Peak Detection of Complex Components and Their Metabolites in Untargeted LC-HRMS Data. Analytica Chimica Acta, 1238; 340189
Zhu, R., J. Gao, M. Li, Q. Gao, X. Wu, and Y. Zhang (2023). A ppb-level Online Detection System for Gas Concentrations in CS2/SO2 Mixtures Based on UV-DOAS Combined with VMD-CNN-TL Model. Sensors and Actuators B: Chemical, 394; 134440
Authors
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.