Extração Automática de Atributos de Sinais de Emissão Acústica com Redes Neurais Autocodificadoras para Predição de Integridade em Tubulações
Resumo
A análise de sinais de Emissão Acústica (EA) é uma técnica amplamente utilizada para monitorar processos de degradação estrutural, como a perda de espessura em tubulações. Contudo, a extração de atributos informativos a partir desses sinais é dificultada por ruídos e pela complexidade física da propagação acústica. Este trabalho propõe uma nova abordagem baseada em Denoising Autoencoders com redes neurais convolucionais para atenuação de ruídos e geração de representações latentes compactas e relevantes. A técnica proposta supera métodos tradicionais de extração de atributos na predição de espessura, especialmente em cenários com alto nível de ruído, utilizando dados sintéticos e reais.
Palavras-chave:
Autocodificador, Aprendizado Profundo, Oleodutos, Integridade
Referências
Aldosari, H., Elfouly, R., and Ammar, R. (2020). Evaluation of machine learning-based regression techniques for prediction of oil and gas pipelines defect. In 2020 International Conference on Computational Science and Computational Intelligence (CSCI), pages 1452–1456.
Bender, R., Féron, D., Mills, D., Ritter, S., Bäßler, R., Bettge, D., De Graeve, I., Dugstad, A., Grassini, S., Hack, T., et al. (2022). Corrosion challenges towards a sustainable society. Materials and corrosion, 73(11):1730–1751.
Heuel, J. and Friederich, W. (2022). Suppression of wind turbine noise from seismological data using nonlinear thresholding and denoising autoencoder. Journal of Seismology, 26(5):913–934.
Kaji, M., Parvizian, J., and van de Venn, H. W. (2020). Constructing a reliable health indicator for bearings using convolutional autoencoder and continuous wavelet transform. Applied Sciences, 10(24).
Keogh, E., Chakrabarti, K., Pazzani, M., and Mehrotra, S. (2001). Dimensionality reduction for fast similarity search in large time series databases. Knowledge and Information Systems, 3(3):263–286.
Li, P., Pei, Y., and Li, J. (2023). A comprehensive survey on design and application of autoencoder in deep learning. Applied Soft Computing, 138:110176.
May, Z., Alam, M., Nayan, N. A., Rahman, N. A. A., and Mahmud, M. S. (2021). Acoustic emission corrosion feature extraction and severity prediction using hybrid wavelet packet transform and linear support vector classifier. Plos one, 16(12):e0261040.
Multiphysics C (1998). Introduction to COMSOL Multiphysics®. COMSOL Multiphysics, Burlington, MA. Accessed February 9, 2018.
Shwartz-Ziv, R. and Armon, A. (2022). Tabular data: Deep learning is not all you need. Information Fusion, 81:84–90.
Song, L., Cui, X., Han, X., Gao, Y., Liu, F., Yu, Y., and Yuan, Y. (2024). A non-metallic pipeline leak size recognition method based on cwt acoustic image transformation and cnn. Applied Acoustics, 225:110180.
Sung, Y., Jeon, H. J., Kim, D., et al. (2024). Internal pipe corrosion assessment method in water distribution system using ultrasound and convolutional neural networks. npj Clean Water, 7:63.
Xiao, R., Hu, Q., and Li, J. (2019). Leak detection of gas pipelines using acoustic signals based on wavelet transform and support vector machine. Measurement, 146:479–489.
Xu, Z.-D., Zhu, C., and Shao, L.-W. (2021). Damage identification of pipeline based on ultrasonic guided wave and wavelet denoising. Journal of Pipeline Systems Engineering and Practice, 12(4):04021051.
Zang, X., Xu, Z.-D., Lu, H., Zhu, C., and Zhang, Z. (2023). Ultrasonic guided wave techniques and applications in pipeline defect detection: A review. International Journal of Pressure Vessels and Piping, 206:105033.
Bender, R., Féron, D., Mills, D., Ritter, S., Bäßler, R., Bettge, D., De Graeve, I., Dugstad, A., Grassini, S., Hack, T., et al. (2022). Corrosion challenges towards a sustainable society. Materials and corrosion, 73(11):1730–1751.
Heuel, J. and Friederich, W. (2022). Suppression of wind turbine noise from seismological data using nonlinear thresholding and denoising autoencoder. Journal of Seismology, 26(5):913–934.
Kaji, M., Parvizian, J., and van de Venn, H. W. (2020). Constructing a reliable health indicator for bearings using convolutional autoencoder and continuous wavelet transform. Applied Sciences, 10(24).
Keogh, E., Chakrabarti, K., Pazzani, M., and Mehrotra, S. (2001). Dimensionality reduction for fast similarity search in large time series databases. Knowledge and Information Systems, 3(3):263–286.
Li, P., Pei, Y., and Li, J. (2023). A comprehensive survey on design and application of autoencoder in deep learning. Applied Soft Computing, 138:110176.
May, Z., Alam, M., Nayan, N. A., Rahman, N. A. A., and Mahmud, M. S. (2021). Acoustic emission corrosion feature extraction and severity prediction using hybrid wavelet packet transform and linear support vector classifier. Plos one, 16(12):e0261040.
Multiphysics C (1998). Introduction to COMSOL Multiphysics®. COMSOL Multiphysics, Burlington, MA. Accessed February 9, 2018.
Shwartz-Ziv, R. and Armon, A. (2022). Tabular data: Deep learning is not all you need. Information Fusion, 81:84–90.
Song, L., Cui, X., Han, X., Gao, Y., Liu, F., Yu, Y., and Yuan, Y. (2024). A non-metallic pipeline leak size recognition method based on cwt acoustic image transformation and cnn. Applied Acoustics, 225:110180.
Sung, Y., Jeon, H. J., Kim, D., et al. (2024). Internal pipe corrosion assessment method in water distribution system using ultrasound and convolutional neural networks. npj Clean Water, 7:63.
Xiao, R., Hu, Q., and Li, J. (2019). Leak detection of gas pipelines using acoustic signals based on wavelet transform and support vector machine. Measurement, 146:479–489.
Xu, Z.-D., Zhu, C., and Shao, L.-W. (2021). Damage identification of pipeline based on ultrasonic guided wave and wavelet denoising. Journal of Pipeline Systems Engineering and Practice, 12(4):04021051.
Zang, X., Xu, Z.-D., Lu, H., Zhu, C., and Zhang, Z. (2023). Ultrasonic guided wave techniques and applications in pipeline defect detection: A review. International Journal of Pressure Vessels and Piping, 206:105033.
Publicado
29/09/2025
Como Citar
DUTRA, Bernardo et al.
Extração Automática de Atributos de Sinais de Emissão Acústica com Redes Neurais Autocodificadoras para Predição de Integridade em Tubulações. In: SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 40. , 2025, Fortaleza/CE.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 935-941.
ISSN 2763-8979.
DOI: https://doi.org/10.5753/sbbd.2025.247810.
