Artificial Intelligence for Gas Leak Detection with Thermal Cameras and Metal Oxide Semiconductor Sensors

Edmilson Sanches; Fábio Augusto; Pauline Silveira; Bernardo Feijó Junqueira; Dimas A. M. Lemes; José Picolo; Guilherme Ribeiro Sales; Valentino Corso; Cides S. Bezerra

doi:10.22456/2175-2745.143526

Authors

Edmilson Sanches CPQD - Centro de Pesquisa e Desenvolvimento https://orcid.org/0009-0009-2235-3417
Fábio Augusto CPQD - Centro de Pesquisa e Desenvolvimento https://orcid.org/0009-0000-7288-3525
Pauline Silveira CPQD - Centro de Pesquisa e Desenvolvimento
Bernardo Feijó Junqueira CPQD - Centro de Pesquisa e Desenvolvimento
Dimas A. M. Lemes Pontifícia Universidade Católica de Campinas (PUCC)
José Picolo Pontifícia Universidade Católica de Campinas (PUCC)
Guilherme Ribeiro Sales CPQD - Centro de Pesquisa e Desenvolvimento
Valentino Corso CPQD - Centro de Pesquisa e Desenvolvimento
Cides S. Bezerra CPQD - Centro de Pesquisa e Desenvolvimento https://orcid.org/0000-0002-3602-1909

DOI:

https://doi.org/10.22456/2175-2745.143526

Keywords:

Gas Leak Detection, AI-powered Solution, Multimodal Data Fusion

Abstract

Early detection of gas leaks is crucial for safety and efficiency in oil platforms and refineries. The presence of various hazardous gases, often imperceptible to human senses, poses significant risks. AI-powered solutions can effectively monitor for gas leaks, improving safety and ensuring efficient operations. In this work we proposed a modular architecture effectively combines tabular data from gas sensors and spatial information from thermal images using a variety of backbones, including MobileNet. By employing dense layers and an optimized training strategy, we achieved state-of-the-art performance, with 100% accuracy, demonstrating the effectiveness of our approach for gas leakage detection.

Downloads

Download data is not yet available.

References

CAZARIM, L. 5 Maiores Acidentes com Plataformas de Petróleo - Jornal Pelicano. ⟨https://www.jornalpelicano.com.br/2014/01/maiores-acidentes-com-plataformas-de-petroleo/⟩. (Acessado em 12/02/2024).

FIGUEIREDO, M. G.; ALVAREZ, D.; ADAMS, R. N. O acidente da plataforma de petróleo P-36 revisitado 15 anos depois: da gestão de situações incidentais e acidentais aos fatores organizacionais. Cadernos de Saúde Pública, SciELO Brasil, v. 34, p. e00034617, 2018.

GUIDA, H. F. S.; FIGUEIREDO, M. G.; HENNINGTON, É. A. Perfil dos acidentes de trabalho fatais em empresa de petróleo no período de 2001 a 2016. Revista Brasileira de Saúde Ocupacional, SciELO Brasil, v. 45, p. e31, 2020.

KOPBAYEV, A. et al. Gas leakage detection using spatial and temporal neural network model. Process Safety and Environmental Protection, v. 160, p. 968–975, 2022. ISSN 0957-5820. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S0957582022001999⟩.

ATTALLAH, O.; MORSI, I. An electronic nose for identifying multiple combustible/harmful gases and their concentration levels via artificial intelligence. Measurement, v. 199, p. 111458, 2022. ISSN 0263-2241. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S0263224122006856⟩.

LUO, J. et al. E-nose system based on Fourier series for gases identification and concentration estimation from food spoilage. IEEE Sensors Journal, v. 23, n. 4, p. 3342–3351, 2023.

NARKHEDE, P. et al. Gas detection and identification using multimodal artificial intelligence based sensor fusion. Applied System Innovation, v. 4, n. 1, 2021. ISSN 2571-5577. Disponível em: ⟨https://www.mdpi.com/2571-5577/4/1/3⟩.

ADEFILA, K.; YAN, Y.; WANG, T. Leakage detection of gaseous CO2 through thermal imaging. In: 2015 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings. [S.l.: s.n.], 2015. p. 261–265.

JADIN, M. S.; GHAZALI, K. H. Gas leakage detection using thermal imaging technique. In: 2014 UKSim-AMSS 16th International Conference on Computer Modelling and Simulation. [S.l.: s.n.], 2014. p. 302–306.

STEFFENS, C. R. et al. On robustness of robotic and autonomous systems perception: An assessment of image distortion on state-of-the-art robotic vision model. Journal of Intelligent & Robotic Systems, Springer, v. 101, p. 1–17, 2021.

RAHATE, A. et al. Employing multimodal co-learning to evaluate the robustness of sensor fusion for industry 5.0 tasks. Soft Computing, Springer, v. 27, n. 7, p. 4139–4155, 2023.

ATTALLAH, O. Multitask deep learning-based pipeline for gas leakage detection via e-nose and thermal imaging multimodal fusion. Chemosensors, v. 11, n. 7, 2023. ISSN 2227-9040. Disponível em: ⟨https://www.mdpi.com/2227-9040/11/7/364⟩.

SHIRLEY, C. et al. Recognition and monitoring of gas leakage using infrared imaging technique with machine learning. Multimedia Tools and Applications, Springer, v. 83, n. 12, p. 35413–35426, 2024.

NARKHEDE, P. et al. MultimodalGasData: Multimodal dataset for gas detection and classification. Data, v. 7, n. 8, 2022. ISSN 2306-5729. Disponível em: ⟨https://www.mdpi.com/2306-5729/7/8/112⟩.

TORREY, L.; SHAVLIK, J. Transfer learning. In: Handbook of research on machine learning applications and trends: algorithms, methods, and techniques. [S.l.]: IGI Global, 2010. p. 242–264.

SANDLER, M. et al. MobileNetV2: Inverted Residuals and Linear Bottlenecks. 2019. Disponível em: ⟨https://arxiv.org/abs/1801.04381⟩.

HUANG, G. et al. Densely Connected Convolutional Networks. 2018. Disponível em: ⟨https://arxiv.org/abs/1608.06993⟩.

HE, K. et al. Identity Mappings in Deep Residual Networks. 2016. Disponível em: ⟨https://arxiv.org/abs/1603.05027⟩.

TAN, M.; LE, Q. V. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. 2020. Disponível em: ⟨https://arxiv.org/abs/1905.11946⟩.

CHOLLET, F. Xception: Deep Learning with Depthwise Separable Convolutions. 2017. Disponível em: ⟨https://arxiv.org/abs/1610.02357⟩.

ZOPH, B. et al. Learning Transferable Architectures for Scalable Image Recognition. 2018. Disponível em: ⟨https://arxiv.org/abs/1707.07012⟩.

SZEGEDY, C. et al. Rethinking the Inception Architecture for Computer Vision. 2015. Disponível em: ⟨https://arxiv.org/abs/1512.00567⟩.

RUSSAKOVSKY, O. et al. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision (IJCV), v. 115, n. 3, p. 211–252, 2015.

FIX, E. Discriminatory analysis: nonparametric discrimination, consistency properties. [S.l.]: USAF School of Aviation Medicine, 1985. v. 1.

GRAVES, A.; GRAVES, A. Long short-term memory. Supervised sequence labelling with recurrent neural networks, Springer, p. 37–45, 2012.

KINGMA, D. P.; BA, J. Adam: A Method for Stochastic Optimization. 2017. Disponível em: ⟨https://arxiv.org/abs/1412.6980⟩.