Detección de anomalías basada en técnicas inteligentes de una planta de obtención de material bicomponente empleado en la fabricación de palas de aerogenerador

  1. Esteban Jove 1
  2. José-Luis Casteleiro-Roca 1
  3. Héctor Quintián 1
  4. Juan Albino Méndez Pérez 2
  5. José Luis Calvo Rolle 1
  1. 1 Univesidade da Coruña,
  2. 2 Universidad de La Laguna

    Universidad de La Laguna

    San Cristobal de La Laguna, España

    GRID grid.10041.34

Revista iberoamericana de automática e informática industrial ( RIAI )

ISSN: 1697-7912

Year of publication: 2020

Volume: 17

Issue: 1

Pages: 84-93

Type: Article

Export: RIS
DOI: 10.4995/riai.2019.11055 DIALNET GOOGLE SCHOLAR lock_openOpen access editor


Technological advances, especially in the industrial field, have led to the development and optimization of the activities that takes place on it. To achieve this goal, an early detection of any kind of anomaly is very important. This can contribute to energy and economic savings and an environmental impact reduction. In a context where the reduction of pollution gasses emission is promoted, the use of alternative energies, specially the wind energy, plays a key role. The wind generator blades are usually manufactured from bicomponent material, obtained from the mixture of two dierent primary components. The present research assesses dierent one-class intelligent techniques to perform anomaly detection on a bicomponent mixing system used on the wind generator manufacturing. To perform the anomaly detection, the intelligent models were obtained from real dataset recorded during the right operation of a bicomponent mixing plant. The classifiers for each technique were validated using artificial outliers, achieving very good results.

Bibliographic References

  • Bradley, A. P., 1997. The use of the area under the roc curve in the evaluation of machine learning algorithms. Pattern Recognition 30 (7), 1145 – 1159.
  • Casale, P., Pujol, O., Radeva, P., 2011. Approximate convex hulls family for one-class classification. In: Sansone, C., Kittler, J., Roli, F. (Eds.), Multiple Classifier Systems. Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 106–115.
  • Casale, P., Pujol, O., Radeva, P., 2014. Approximate polytope ensemble for oneclass classification. Pattern Recognition 47 (2), 854 – 864.
  • Chandola, V., Banerjee, A., Kumar, V., 2009. Anomaly detection: A survey. ACM computing surveys (CSUR) 41 (3), 15.
  • Chen, Y., Zhou, X. S., Huang, T. S., 2001. One-class svm for learning in image retrieval. In: Image Processing, 2001. Proceedings. 2001 International Conference on. Vol. 1. IEEE, pp. 34–37.
  • Chiang, L. H., Russell, E. L., Braatz, R. D., 2000. Fault detection and diagnosis in industrial systems. Springer Science & Business Media.
  • de la Portilla, M. P., Piñeiro, A. L., Sánchez, J. A. S., Herrera, R. M., 2017. Modelado dinámico y control de un dispositivo sumergido provisto de actuadores hidrostáticos. Revista Iberoamericana de Automtica e Informática industrial 15 (1), 12–23.
  • Fan, H.,Wong, C., Yuen, M.-F., April 2006. Prediction of material properties of epoxy materials using molecular dynamic simulation. In: Thermal, Mechanical and Multiphysics Simulation and Experiments in Micro-Electronics and Micro-Systems, 2006. EuroSime 2006. 7th International Conference on. pp. 1–4.
  • Fernández-Francos, D., Fontenla-Romero, O., Alonso-Betanzos, A., 2018. One-class convex hull-based algorithm for classification in distributed environments. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 1–11.
  • González, G., Angelo, C. D., Forchetti, D., Aligia, D., 2018. Diagnósico de fallas en el convertidor del rotor en generadores de inducción con rotor bobinado. Revista Iberoamericana de Automática e Informática industrial 15 (3), 297–308.
  • Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y., 2016. Deep learning. Vol. 1. MIT press Cambridge.
  • Heller, K. A., Svore, K. M., Keromytis, A. D., Stolfo, S. J., 2003. One class support vector machines for detecting anomalous windows registry accesses. In: Proc. of the workshop on Data Mining for Computer Security. Vol. 9.
  • Hobday, M., 1998. Product complexity, innovation and industrial organisation. Research policy 26 (6), 689–710.
  • Hodge, V., Austin, J., 2004. A survey of outlier detection methodologies. Artificial intelligence review 22 (2), 85–126.
  • Hwang, B., Cho, S., 1999. Characteristics of auto-associative mlp as a novelty detector. In: Neural Networks, 1999. IJCNN’99. International Joint Conference on. Vol. 5. IEEE, pp. 3086–3091.
  • Jove, E., Casteleiro-Roca, J.-L., Quintián, H., Méndez-Pérez, J. A., Calvo-Rolle, J. L., 2018. A new approach for system malfunctioning over an industrial system control loop based on unsupervised techniques. In: Graña, M., López-Guede, J. M., Etxaniz, O., Herrero, Á., Sáez, J. A., Quintián, H., Corchado, E. (Eds.), International Joint Conference SOCO’18-CISIS’18- ICEUTE’18. Springer International Publishing, Cham, pp. 415–425.
  • Krstajic, D., Buturovic, L. J., Leahy, D. E., Thomas, S., Mar 2014. Crossvalidation pitfalls when selecting and assessing regression and classification models. Journal of Cheminformatics 6 (1), 10. URL:
  • Li, K.-L., Huang, H.-K., Tian, S.-F., Xu, W., 2003. Improving one-class svm for anomaly detection. In: Machine Learning and Cybernetics, 2003 International Conference on. Vol. 5. IEEE, pp. 3077–3081.
  • Miljkovic, D., 2011. Fault detection methods: A literature survey. In: MIPRO, 2011 proceedings of the 34th international convention. IEEE, pp. 750–755.
  • Sakurada, M., Yairi, T., 2014. Anomaly detection using autoencoders with nonlinear dimensionality reduction. In: Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis. ACM, p. 4
  • Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., Williamson, R. C., 2001. Estimating the support of a high-dimensional distribution. Neural computation 13 (7), 1443–1471.
  • Schwartz, J., 1994. Air pollution and daily mortality: A review and meta analysis. Environmental Research 64 (1), 36 – 52.
  • Shalabi, L. A., Shaaban, Z., May 2006. Normalization as a preprocessing engine for data mining and the approach of preference matrix. In: 2006 International Conference on Dependability of Computer Systems. pp. 207–214.
  • Tax, D., Jan 2018. Ddtools, the data description toolbox for matlab. Version 2.1.3.
  • Tax, D. M. J., 2001. One-class classification: concept-learning in the absence of counter-examples [ph. d. thesis]. Delft University of Technology.
  • Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.-A., 2010. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research 11 (Dec), 3371–3408.
  • Wei, X., Huang, G., Li, Y., Aug 2007. Mahalanobis ellipsoidal learning machine for one class classification. In: 2007 International Conference on Machine Learning and Cybernetics. Vol. 6. pp. 3528–3533.
  • Westerhuis, J. A., Gurden, S. P., Smilde, A. K., 2000. Generalized contribution plots in multivariate statistical process monitoring. Chemometrics and intelligent laboratory systems 51 (1), 95–114.
  • Wu, J., Zhang, X., 2001. A pca classifier and its application in vehicle detection. In: IJCNN’01. International Joint Conference on Neural Networks. Proceedings (Cat. No. 01CH37222). Vol. 1. IEEE, pp. 600–604.
  • Young, W.-B., Wu, W.-H., Aug 2011. Optimization of the skin thickness distribution in the composite wind turbine blade. In: Fluid Power and Mechatronics (FPM), 2011 International Conference on. pp. 62–66.
  • Zeng, Z., Wang, J., 2010. Advances in neural network research and applications, 1st Edition. Springer Publishing Company, Incorporated.
  • Zuo, Y., Liu, H., June 2012. Evaluation on comprehensive benefit of wind power generation and utilization of wind energy. In: Software Engineering and Service Science (ICSESS), 2012 IEEE 3rd International Conference on. pp. 635–638.