Abstract
In recent years, due to the increase in computational power, the field of artificial intelligence focused on image classification has undergone a great development. Classical pattern-based methods have serious problems in achieving effective algorithms that fail as less as possible, and are often heavily influenced by environmental variables such as light, changes in the image format, etc. Convolutional Neural Networks are particularly effective as image classifiers, and a good solution to this problem, but they do not completely close the issue. An image classifier indicates the elements, in this case, defects within an image that contain a piece or component but does not give more information. In this work, an implementation of a hybrid neural network system based on two neural networks is proposed. The output of the first one feeds the input of the second one, so that a more robust and efficient algorithm is generated. The combination of an image classifier with linear classifiers will be studied in order to obtain a decision on a real manufacturing part.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Anand, R., Shanthi, T.: Face recognition and classification using GoogleNET architecture. In: Soft Computing for Problem Solving, pp. 261–269. Springer (2020)
Babatunde, H., Folorunso, O., Akinwale, A.: A cellular neural network-based model for edge detection. J. Inf. Comput. Sci. 5(1), 003–010 (2010)
Fujita, T., Okamura, T.: CAM 2-universal machine: a DTCNN implementation for real-time image processing. In: 2008 11th International Workshop on Cellular Neural Networks and Their Applications, pp. 219–223. IEEE (2008)
Fukushima, K., Miyake, S., Ito, T.: Neocognitron: a neural network model for a mechanism of visual pattern recognition. IEEE Trans. Syst. Man Cybern. 5, 826–834 (1983)
Garcia Marquez, F.P., Aea, P.M.: Optimal dynamic analysis of electrical\(/\)electronic components in wind turbines. Energies 10(8), 1111 (2017)
García Márquez, F.P., Segovia Ramírez, I., Pliego Marugán, A.: Decision making using logical decision tree and binary decision diagrams: a real case study of wind turbine manufacturing. Energies 12(9), 1753 (2019)
Gómez Muñoz, C.Q., Aea, A.J.: Cracks and welds detection approach in solar receiver tubes employing electromagnetic acoustic transducers. Struct. Health Monit. 17(5), 1046–1055 (2018)
Gómez Muñoz, C.Q., García Márquez, F.P.: A heuristic method for detecting and locating faults employing electromagnetic acoustic transducers. Eksploatacja i Niezawodność 19(4), 493 (2015)
Gómez Muñoz, C.Q., García Márquez, F.P.: Structural health monitoring for delamination detection and location in wind turbine blades employing guided waves. Wind Energy 22(5), 698–711 (2019)
Herraiz, Á.H., Marugán, A.P., Márquez, F.P.G.: Photovoltaic plant condition monitoring using thermal images analysis by convolutional neural network-based structure. Renew. Energy 153, 334–348 (2020)
Howard, A.G., Zhu, M.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:170404861 (2017)
Jiménez, A.A., Lea, Z.: Maintenance management based on machine learning and nonlinear features in wind turbines. Renew. Energy 146, 316–328 (2020)
Jimenez, A.A., Muñoz, C.Q.G., Márquez, F.P.G.: Dirt and mud detection and diagnosis on a wind turbine blade employing guided waves and supervised learning classifiers. Reliab. Eng. Syst. Saf. 184, 2–12 (2019)
Juan, R.Q., Mario, C.M.: Redes neuronales artificiales para el procesamiento de imágenes, una revisión de la última década. RIEE&C, Revista de Ingeniería Eléctrica, Electrónica y Computación 9(1), 7–16 (2011)
Keerthi, S.S., Gilbert, E.G.: Convergence of a generalized SMO algorithm for SVM classifier design. Mach. Learn. 46(1), 351–360 (2002)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Limonova, E., Alfonso, D.: ResNet-like architecture with low hardware requirements (2020)
Márquez, F.P.G.: A new method for maintenance management employing principal component analysis. Struct. Durab. Health Monit. 6(2), 89 (2010)
Marugán, A.P., Chacón, A.M.P., Márquez, F.P.G.: Reliability analysis of detecting false alarms that employ neural networks: a real case study on wind turbines. Reliab. Eng. Syst. Saf. 191(106), 574 (2019)
Muñoz, C.Q.G., Marquez, F.P.: New pipe notch detection and location method for short distances employing ultrasonic guided waves. Acta Acustica united with Acustica 103(5), 772–781 (2017)
Nishizono, K., Nishio, Y.: Image processing of gray scale images by fuzzy cellular neural network. In: RISP International Workshop nonlinear circuits, Honolulu Hawaii, USA, pp. 90–93 (2006)
Pliego Marugán, A., García Márquez, F.P.: A novel approach to diagnostic and prognostic evaluations applied to railways: a real case study. Proc. Inst. Mech. Eng. Part F: J. Rail Rapid Transit 230(5), 1440–1456 (2016)
Pliego Marugán, A., García Márquez, F.P.: Advanced analytics for detection and diagnosis of false alarms and faults: a real case study. Wind Energy 22(11), 1622–1635 (2019)
Pliego Marugán, A., García Márquez, F.P., Lorente, J.: Decision making process via binary decision diagram. Int. J. Manag. Sci. Eng. Manag. 10(1), 3–8 (2015)
Pliego Marugán, A., Garcia Marquez, F.P., Lev, B.: Optimal decision-making via binary decision diagrams for investments under a risky environment. Int. J. Prod. Res. 55(18), 5271–5286 (2017)
Ramirez, I.S., Muñoz, C.Q.G., Marquez, F.P.G.: A condition monitoring system for blades of wind turbine maintenance management. In: Proceedings of the Tenth International Conference on Management Science and Engineering Management, pp. 3–11. Springer (2017)
Riverola, F.F., Corchado, J.M.: Sistemas híbridos neuro-simbólicos: una revisión. Inteligencia Artificial Revista Iberoamericana de Inteligencia Artificial 4(11), 12–26 (2000)
Seiffert, C., Khoshgoftaar, T.M.: RUSBoost: a hybrid approach to alleviating class imbalance. IEEE Trans. Syst. Man Cybern.-Part A: Syst. Hum. 40(1), 185–197 (2009)
Targ, S., Almeida, D., Lyman, K.: ResNet in resNet: generalizing residual architectures (2016)
Vasavi, S., Priyadarshini, N.K., Vardhan, K.H.: Invariant feature based darknet architecture for moving object classification. IEEE Sens. J. 21, 11417–11426 (2020)
Zhao, W., Chellappa, R., Nandhakumar, N.: Empirical performance analysis of linear discriminant classifiers. In: Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No. 98CB36231), pp 164–169. IEEE (1998)
Acknowledgements
The work reported herewith has been financially by the Universidad Europea de Madrid and the Dirección General de Universidades, Investigación e Innovación of Castilla-La Mancha, under Research Grant ProSeaWind project (Ref.: SBPLY/19/180501/000102). The authors are thankful to Defta Spain S.L.U. company.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ortega Sanz, D., Gomez Muñoz, C.Q., García Márquez, F.P. (2021). Engineering Management for Fault Detection System Using Convolutional Neural Networks. In: Xu, J., García Márquez, F.P., Ali Hassan, M.H., Duca, G., Hajiyev, A., Altiparmak, F. (eds) Proceedings of the Fifteenth International Conference on Management Science and Engineering Management. ICMSEM 2021. Lecture Notes on Data Engineering and Communications Technologies, vol 78. Springer, Cham. https://doi.org/10.1007/978-3-030-79203-9_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-79203-9_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-79202-2
Online ISBN: 978-3-030-79203-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)