Uso de uma rede neural convolucional unidimensional para detecção de falhas em processos industriais

• Antonio Loca UFES
• Thomas Rauber UFES

Abstract

In this paper we present the use of deep learning in the context of fault detection in industrial processes. A Convolutional Artificial Neural Network composed by a 1D convolution architecture is used. A feature selection proposal based on Spearman's rank correlation coefficient is presented, aiming at obtaining an efficient fault identification system with optimized performance in one-dimensional signals. The Tennessee Eastman Process chemical process simulator is used to evaluate the performance of the solution.

References

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.