DOI:
https://doi.org/10.14483/22484728.18432Publicado:
2019-12-06Número:
Vol. 2 Núm. 2 (2019): Edición especialSección:
Visión InvestigadoraIdentification and fault detection in actuator using NN-NARX
Identificación y detección de fallas en accionamiento utilizando NN-NARX
Palabras clave:
Detección de fallas, Monitorización, Redes NN-NARX, Generación de residuos, Identificación de sistemas (es).Palabras clave:
Fault detection, Monitoring, NN-NARX networks, Residual generation, System identification (en).Descargas
Resumen (en)
In this paper, the use of a Nonlinear Auto Regressive eXogenous Neural Networks model or NN-NARX for identification and fault detection in the actuator of an industrial thermal process is presented. Initially, the techniques of fault detection and diagnosis are exposed; then, emphasis is placed on the models of Artificial Neural Networks for identification and fault detection. Subsequently, the control system of a thermal process used as a case study is described. A monitoring system allows data recording under normal operation conditions for identification using the NN-NARX model. The model is used for residual online generation due to faults that are introduced randomly. Finally, the results of residual generation and evaluation are presented. The designed system is useful for implementation through a hardware device that can be incorporated into the process equipment and support the operator in the presence of failures.
Resumen (es)
En este artículo se presenta la utilización de un modelo de Red Neuronal no lineal Auto Regresivo de Variable Exógena o NN-NARX (por sus siglas en inglés), para la identificación y detección de fallas en un accionamiento de un proceso térmico industrial. Inicialmente, se exponen las técnicas de detección y diagnóstico de fallas; luego, se hace énfasis en los modelos de Redes Neuronales Artificiales para identificación y detección de fallas. Posteriormente, se describe el sistema de control de un proceso térmico utilizado como caso de estudio. Un sistema de monitorización permite el registro de datos en condiciones normales de operación para la identificación usando el modelo NN-NARX. El modelo es utilizado para la generación en línea de residuos ante fallas que son introducidas aleatoriamente. Finalmente, se presentan los resultados de la generación y evaluación de residuos. El sistema diseñado es útil para la implementación a través de un dispositivo hardware que puede incorporarse en el equipo del proceso y apoyar al operador ante la presencia de fallas.
Referencias
L. Hurtado, E. Villarreal, and L. Villarreal, “Detección y diagnóstico de fallas mediante técnicas de inteligencia artificial, un estado del arte”. Dyna, vol. 83, no. 199, pp. 19–28, December 2016. https://doi.org/10.15446/dyna.v83n199.55612
Z. Bluvband, and P. Grabov, “Failure Analysis of FMEA”, Proceedings of Annual Reliability and Maintainability Symposium (RAMS), Fort Worth, 2009, pp. 344-347. https://doi.org/10.1109/RAMS.2009.4914700
V. Venkatasubramanian, R. Rengaswamy, K. Yin and S. Kavuri, “A review of process fault detection and diagnosis: Part I: Quantitative model-based methods”. Computers & Chemical Engineering, vol. 27, no. 3, pp. 293-311, March 2003. https://doi.org/10.1016/S0098-1354(02)00160-6
F. E. Pineda and A. Chica, “Proposal of a fault estimation using coprime fractions”. Visión Electrónica, vol.9, no. 2, pp. 172-181, December 2015. DOI: https://doi.org/10.14483/22484728.11025
V. Venkatasubramanian, R. Rengaswamy, K. Yin and S. Kavuri, “A review of process fault detection and diagnosis: Part II: Qualitative models and search strategies”. Computers & Chemical Engineering, vol. 27, no. 3, pp. 313-326, March 2003. DOI: https://doi.org/10.1016/S0098-1354(02)00161-8
V. Venkatasubramanian, R. Rengaswamy, K. Yin and S. Kavuri, “A review of process fault detection and diagnosis: Part III: Process history-based methods”. Computers & Chemical Engineering, vol. 27, no. 3, pp. 327-346, March 2003. DOI: https://doi.org/10.1016/S0098-1354(02)00162-X
G. Biswas, M. Cordier, J. Lunze, L. Trave-Massuyes, L. and Staroswiecki, M., “Diagnosis of Complex Systems: Bridging the Methodologies of the FDI and DX Communities”. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 34, no. 5, pp. 2159-2162, October 2004. https://doi.org/10.1109/TSMCB.2004.835006
Y. Kourd, D. Lefebvre and N. Guersi, “Early FDI Based on Residuals Design According to the Analysis of Models of Faults: Application to DAMADICS”. Advances in Artificial Neural, Vol. 2011, pp. 1-10, July 2011. http://dx.doi.org/10.1155/2011/453169
K. Bruton, P. Raftery, B. Kennedy, M. Keane and D. O’Sullivan, “Review of automated fault detection and diagnostic tools in air handling units”. Energy Efficiency, Vol. 7, issue 2, pp. 335-351, 2014. https://doi.org/10.1007/s12053-013-9238-2
S. Samanta, N. Bera, and G. Sarkar, “An Intelligent Adaptive Neuro Fuzzy based Fault Diagnosis System for Severity and Phase Detection of Induction Machine”. Lectures on Modelling and Simulation; A selection from AMSE # 2017-N°2, pp. 41-51, November 2017.
J. Jang, “ANFIS: Adaptive Network-Based Fuzzy Inference Systems”. IEEE Trans. on Systems, Man and Cybernetics, Vol. 23, pp. 665-685, 1993. https://doi.org/10.1109/21.256541
R. Fulles, “Neural Fuzzy Systems”. Finland: Abo Akademy University, 1995. ISBN: 951-650-624.
L. Hurtado, “Utilización de anfis para la detección de fallas en un Sistema térmico”. Memorias del IV Congreso Internacional de Ingeniería Informática y Sistemas de Información, Vol. 19, 2018, pp. 212-223.
R. Araujo, A. Oliveira and S. Meira, “A morphological neural network for binary classification problems”. Engineering Applications of Artificial Intelligence, vol. 65, pp. 12-28, October 2017. https://doi.org/10.1016/j.engappai.2017.07.014
L. Hurtado, “Modelamiento teórico y modelamiento empírico de procesos, una síntesis”, Revista Scientia et Technica, año 12, no. 31, pp. 103 – 138, August 2006. http://dx.doi.org/10.22517/23447214.6399
S. Yu, K. Zhu and X. H. Zhang, “Energy demand projection of China using a path-coefficient analysis and PSO–GA approach”. Energy Conversion and Management, vol. 53, no. 1, pp. 142-153, January 2012. https://doi.org/10.1016/j.enconman.2011.08.015
E. Pisoni, M. Farina, C. Carnevale and L. Piroddi, “Forecasting peak air pollution levels using NARX models”. Engineering Applications of Artificial Intelligence, vol. 22, issues 4-5, pp. 593-602, June 2009. https://doi.org/10.1016/j.engappai.2009.04.002
L. G. Baca, M. Pegalajar, M. Delgado and M. Pegalajar, “An Application of Non-Linear Autoregressive Neural Networks to Predict Energy Consumption in Public Buildings”. Energies, vol. 9, issue 9:684, August 2016. https://doi.org/10.3390/en9090684
S. Chen, S.A. Billings and P. M. Grant, “Non-linear system identification using neural networks”, International Journal of Control, vol. 51, issue 6, pp. 1191-1214, March 2007. https://doi.org/10.1080/00207179008934126
E. Cadenas, W. Rivera, R. Campos and C. Heard, “Wind Speed Prediction Using a Univariate ARIMA Model and a Multivariate NARX Model”. Energies, vol. 9, issue 2:109, February 2016. https://doi.org/10.3390/en9020109
Amatrol, Thermal Process Control System, T5553 equipment manual.
Cómo citar
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Descargar cita
Licencia
Derechos de autor 2019 Visión electrónica
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial 4.0.
.png)
atribución- no comercial 4.0 International
.jpg)
