Uso de uma rede neural convolucional unidimensional para detecção de falhas em processos industriais
Resumo
Neste artigo é apresentado o uso de aprendizagem profunda - Deep Learning, no contexto de detecção de falhas em processos industriais. É empregada uma Rede Neural Artificial Convolucional composta por uma arquitetura de convolução 1D. Apresenta-se uma proposta de seleção de características baseada no coeficiente de correlação de postos de Spearman visando à obtenção de um sistema eficiente de identificação de falhas com desempenho otimizado em sinais unidimensionais. O simulador de processo químico Tennessee Eastman Process é utilizado a fim de avaliar o desempenho da solução.
Referências
Abdeljaber, O., Avci, O., Kiranyaz, M. S., Boashash, B., Sodano, H., & Inman, D. J. (2018). 1-D CNNs for structural damage detection: verification on a structural health monitoring benchmark data. Neurocomputing, 275, 1308-1317. Disponível em: . Acesso em: 20 jan. 2019.
Chollet, F. (2015). Keras. Disponível em:. Acesso em: 20 jan. 2019.
Guo, M. F., Zeng, X. D., Chen, D. Y., & Yang, N. C. (2018). Deep-Learning-Based Earth Fault Detection Using Continuous Wavelet Transform and Convolutional Neural Network in Resonant Grounding Distribution Systems. IEEE Sensors Journal, 18(3), 1291-1300.Disponível em:. Acesso em: 20 jan. 2019.
Guo, T., Dong, J., Li, H., & Gao, Y. (2017, March). Simple convolutional neural network on image classification. In 2017 IEEE 2nd International Conference on Big Data Analysis (ICBDA)( (pp. 721-724). IEEE. Disponível em:>. Acesso em: 20 jan. 2019.
Lekha, S., & Suchetha, M. (2018). Real-Time Non-Invasive Detection and Classification of Diabetes Using Modified Convolution Neural Network. IEEE journal of biomedical and health informatics, 22(5), 1630-1636. Disponível em:. Acesso em: 22 jan. 2019.
Liu, Z., Meng, X. A., Cui, J., Huang, Z., & Wu, J. (2018, October). Automatic Identification of Abnormalities in 12-Lead ECGs Using Expert Features and Convolutional Neural Networks. In 2018 International Conference on Sensor Networks and Signal Processing (SNSP) (pp. 163-167). IEEE. Disponivel em:. Acesso em: 26 jan. 2019.
Mukaka, M. M. (2012). A guide to appropriate use of correlation coefficient in medical research. Malawi Medical Journal, 24(3), 69-71. Disponível em: < https://www.ajol.info/index.php/mmj/article/download/81576/71739>. Acesso em: 21 jan. 2019.
Paoletti, M. E., Haut, J. M., Plaza, J., & Plaza, A. (2018). A new deep convolutional neural network for fast hyperspectral image classification. ISPRS journal of photogrammetry and remote sensing, 145, 120-147.
Disponível em: < https://www.sciencedirect.com/science/article/pii/S0924271617303660>. Acesso em: 20 jan. 2019.
Wu, H., & Zhao, J. (2018). Deep convolutional neural network model based chemical process fault diagnosis. Computers & Chemical Engineering, 115, 185-197. Disponível em:. Acesso em: 20 jan. 2019.
Zilong, Z., & Wei, Q. (2018, March). Intelligent fault diagnosis of rolling bearing using one-dimensional multi-scale deep convolutional neural network based health state classification. In Networking, Sensing and Control (ICNSC), 2018 IEEE 15th International Conference on (pp. 1-6). IEEE. Disponível em:. Acesso em: 20 jan. 2019.
Chollet, F. (2015). Keras. Disponível em:
Guo, M. F., Zeng, X. D., Chen, D. Y., & Yang, N. C. (2018). Deep-Learning-Based Earth Fault Detection Using Continuous Wavelet Transform and Convolutional Neural Network in Resonant Grounding Distribution Systems. IEEE Sensors Journal, 18(3), 1291-1300.Disponível em:
Guo, T., Dong, J., Li, H., & Gao, Y. (2017, March). Simple convolutional neural network on image classification. In 2017 IEEE 2nd International Conference on Big Data Analysis (ICBDA)( (pp. 721-724). IEEE. Disponível em:
Lekha, S., & Suchetha, M. (2018). Real-Time Non-Invasive Detection and Classification of Diabetes Using Modified Convolution Neural Network. IEEE journal of biomedical and health informatics, 22(5), 1630-1636. Disponível em:
Liu, Z., Meng, X. A., Cui, J., Huang, Z., & Wu, J. (2018, October). Automatic Identification of Abnormalities in 12-Lead ECGs Using Expert Features and Convolutional Neural Networks. In 2018 International Conference on Sensor Networks and Signal Processing (SNSP) (pp. 163-167). IEEE. Disponivel em:
Mukaka, M. M. (2012). A guide to appropriate use of correlation coefficient in medical research. Malawi Medical Journal, 24(3), 69-71. Disponível em: < https://www.ajol.info/index.php/mmj/article/download/81576/71739>. Acesso em: 21 jan. 2019.
Paoletti, M. E., Haut, J. M., Plaza, J., & Plaza, A. (2018). A new deep convolutional neural network for fast hyperspectral image classification. ISPRS journal of photogrammetry and remote sensing, 145, 120-147.
Disponível em: < https://www.sciencedirect.com/science/article/pii/S0924271617303660>. Acesso em: 20 jan. 2019.
Wu, H., & Zhao, J. (2018). Deep convolutional neural network model based chemical process fault diagnosis. Computers & Chemical Engineering, 115, 185-197. Disponível em:
Zilong, Z., & Wei, Q. (2018, March). Intelligent fault diagnosis of rolling bearing using one-dimensional multi-scale deep convolutional neural network based health state classification. In Networking, Sensing and Control (ICNSC), 2018 IEEE 15th International Conference on (pp. 1-6). IEEE. Disponível em:
Publicado
09/04/2019
Como Citar
LOCA, Antonio; RAUBER, Thomas .
Uso de uma rede neural convolucional unidimensional para detecção de falhas em processos industriais. In: ESCOLA REGIONAL DE COMPUTAÇÃO BAHIA, ALAGOAS E SERGIPE (ERBASE) , 2019, Ilhéus.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 42-47.
