Analysis of Neural Network Training Algorithms for Implementation of the Prescriptive Maintenance Strategy
LEMPA Paweł and FILO Grzegorz
download PDFAbstract. This paper presents a proposal to combine supervised and semi-supervised training strategies to obtain a neural network for use in the prescriptive maintenance approach. It is required in this approach because of only partially labelled data for use in supervised learning, and additionally, this data is predicted to expand quickly. The main issue is the decision on which are suitable training methodologies for supervised learning, having in mind using this data and methods for semi-supervised learning. The proposed methods of training neural networks with supervised and semi-supervised training to receive the best results will be tested and compared in further work.
Keywords
Neural Network Training, Multilayer Network Training, Supervised Training, Semi-Supervised Training, Prescriptive Maintenance
Published online 7/20/2022, 7 pages
Copyright © 2022 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: LEMPA Paweł and FILO Grzegorz, Analysis of Neural Network Training Algorithms for Implementation of the Prescriptive Maintenance Strategy, Materials Research Proceedings, Vol. 24, pp 281-287, 2022
DOI: https://doi.org/10.21741/9781644902059-41
The article was published as article 41 of the book Terotechnology XII
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] K. Lepenioti, A. Bousdekis, D. Apostolou, G. Mentzas. Prescriptive analytics: Literature review and research challenges, International Journal of Information Management 50 (2020) 57-70. https://doi.org/10.1016/j.ijinfomgt.2019.04.003
[2] R. He, X. Li, G. Chen, G. Chen, Y. Liu. Generative adversarial network-based semi-supervised learning for real-time risk warning of process industries, Expert Systems with Applications 150 (2020) art. 113244. https://doi.org/10.1016/j.eswa.2020.113244
[3] R. Raina, A. Battle, H. Lee, B. Packer, A.Y. Ng. Self-taught learning: transfer learning from unlabeled data ACM International Conference Proceeding 227 (2007) 759-766. https://doi.org/10.1145/1273496.1273592
[4] I. Goodfellow, Y. Bengio, A. Courville, Deep Learning. MIT Press, November 2016, ISBN 9780262035613
[5] G. Englund, O. Sarnelle, S.D. Cooper. The importance of data‐selection criteria: meta‐analyses of stream predation experiments, Ecology 80 (1999) 1132-1141. https://doi.org/10.1890/0012-9658(1999)080[1132:TIODSC]2.0.CO;2
[6] Z. Hatush, M. Skitmore. Evaluating contractor prequalification data: selection criteria and project success factors, Construction Management and Economics 15 (1997) 129-147. https://doi.org/10.1080/01446199700000002
[7] M. Frasca, A. Bertoni, M. Re, G. Valentini. A neural network algorithm for semi-supervised node label learning from unbalanced data, Neural Networks 43 (2013) 84-98. https://doi.org/10.1016/j.neunet.2013.01.021
[8] P. P. Bedekar, S. R.Bhide, V. S. Kale. Fault section estimation in power system using Hebb’s rule and continuous genetic algorithm, International Journal of Electrical Power & Energy Systems 33 (2011) 457-465. https://doi.org/10.1016/j.ijepes.2010.10.008
[9] B.S. Yang, T. Han, J.L. An. ART-KOHONEN neural network for fault diagnosis of rotating machinery, Mech. Sys. and Signal Proc. 18 (2004) 645-657. https://doi.org/10.1016/S0888-3270(03)00073-6
[10] F. A. Souza, M. F. Castoldi, A. Goedtel, M. da Silva. A cascade perceptron and Kohonen network approach to fault location in rural distribution feeders, Applied Soft Computing 96 (2020) art. 106627. https://doi.org/10.1016/j.asoc.2020.106627
[11] Z. Chen, X. Yuan, M. Sun, J. Gao, P. Li. A hybrid deep computation model for feature learning on aero-engine data: applications to fault detection, Applied Mathematical Modelling 83 (2020) 487-496. https://doi.org/10.1016/j.apm.2020.02.002
[12] A. Pretorius, H. Kamper, S. Kroon. On the expected behaviour of noise regularised deep neural networks as Gaussian processes. Pattern Rec. Letters 138 (2020) 75-81. https://doi.org/10.1016/j.patrec.2020.06.027
[13] N. Didcock, S. Jakubek, H.-M. Kögeler. Regularisation methods for neural network model averaging, Engineering Applications of Artificial Intelligence 41 (2015) 128-138. https://doi.org/10.1016/j.engappai.2015.02.005
[14] W. Li, W. Wang, X. Wang, S. Liu, L. Pei, F. Guo. A dynamic relearning neural network model for time series analysis of online marine data, Computers & Geosciences 73 (2014) 99-107. https://doi.org/10.1016/j.cageo.2014.09.006
[15] W. Jiang, Z. Song, J. Zhan, Z. He, X. Wen, K. Jiang. Optimized co-scheduling of mixed-precision neural network accelerator for real-time multitasking applications, Journal of Systems Architecture 110 (2020) art. 101775. https://doi.org/10.1016/j.sysarc.2020.101775
[16] J. Pietraszek, A. Gadek-Moszczak, N. Radek. The estimation of accuracy for the neural network approximation in the case of sintered metal properties. Studies in Computational Intelligence 513 (2014) 125-134. https://doi.org/10.1007/978-3-319-01787-7_12
[17] J. Pietraszek, R. Dwornicka, A. Szczotok. The bootstrap approach to the statistical significance of parameters in the fixed effects model. ECCOMAS 2016 – Proc. 7th European Congress on Computational Methods in Applied Sciences and Engineering 3, 6061-6068. https://doi.org/10.7712/100016.2240.9206
[18] A. Szczotok, J. Pietraszek, N. Radek. Metallographic Study and Repeatability Analysis of γ’ Phase Precipitates in Cored, Thin-Walled Castings Made from IN713C Superalloy. Archives of Metallurgy and Materials 62 (2017) 595-601. https://doi.org/10.1515/amm-2017-0088
[19] J. Pietraszek, A. Szczotok, N. Radek. The fixed-effects analysis of the relation between SDAS and carbides for the airfoil blade traces. Archives of Metallurgy and Materials 62 (2017) 235-239. https://doi.org/10.1515/amm-2017-0035
[20] N. Radek, J. Pietraszek, A. Goroshko. The impact of laser welding parameters on the mechanical properties of the weld, AIP Conf. Proc. 2017 (2018) art.20025. https://doi.org/10.1063/1.5056288
[21] N. Radek, J. Pietraszek, A. Gadek-Moszczak, Ł.J. Orman, A. Szczotok. The morphology and mechanical properties of ESD coatings before and after laser beam machining, Materials 13 (2020) art. 2331. https://doi.org/10.3390/ma13102331
[22] N. Radek, J. Konstanty, J. Pietraszek, Ł.J. Orman, M. Szczepaniak, D. Przestacki. The effect of laser beam processing on the properties of WC-Co coatings deposited on steel. Materials 14 (2021) art. 538. https://doi.org/10.3390/ma14030538
[23] M. Kekez, L. Radziszewski, A. Sapietova. Fuel type recognition by classifiers developed with computational intelligence methods using combustion pressure data and the crankshaft angle at which heat release reaches its maximum, Procedia Engineering 136 (2016) 353-358. https://doi.org/10.1016/j.proeng.2016.01.222
[24] T. Lipiński. Corrosion resistance of 1.4362 steel in boiling 65% nitric acid, Manufacturing Technology 16 (2016) 1004-1009.
[25] Ł.J. Orman Ł.J., N. Radek, J. Pietraszek, M. Szczepaniak. Analysis of enhanced pool boiling heat transfer on laser-textured surfaces. Energies 13 (2020) art. 2700. https://doi.org/10.3390/en13112700
[26] M. Zmindak, L. Radziszewski, Z. Pelagic, M. Falat. FEM/BEM techniques for modelling of local fields in contact mechanics, Communications – Scientific Letters of the University of Zilina 17 (2015) 37-46.
[27] A. Kubecki, C. Śliwiński, J. Śliwiński, I. Lubach, L. Bogdan, W. Maliszewski. Assessment of the technical condition of mines with mechanical fuses, Technical Transactions 118 (2021) art. e2021025. https://doi.org/10.37705/TechTrans/e2021025
[28] S. Marković, D. Arsić, R.R. Nikolić, V. Lazić, B. Hadzima, V.P. Milovanović, R. Dwornicka, R. Ulewicz. Exploitation characteristics of teeth flanks of gears regenerated by three hard-facing procedures, Materials 14 (20210 art. 4203. https://doi.org/10.3390/ma14154203
[29] G. Majewski, M. Telejko, Ł.J. Orman. Preliminary results of thermal comfort analysis in selected buildings, E3S Web of Conf. 17 (2017) art. 56. https://doi.org/10.1051/e3sconf/20171700056
[30] M. Dobrzański. The influence of water price and the number of residents on the economic efficiency of water recovery from grey water, Technical Transactions 118 (2021) art. e2021001. https://doi.org/10.37705/TechTrans/e2021001
[31] B. Szczodrowska, R. Mazurczuk. A review of modern materials used in military camouflage within the radar frequency range, Technical Transactions 118 (2021) art.e2021003. https://doi.org/10.37705/TechTrans/e2021003
[32] M. Morawski,T. Talarczyk, M. Malec. Depth control for biomimetic and hybrid unmanned underwater vehicles, Technical Transactions 118 (2021) art. e2021024. https://doi.org/10.37705/TechTrans/e2021024
[33] T. Styrylska, J. Pietraszek. Numerical modeling of non-steady-state temperature-fields with supplementary data. Zeitschrift fur Angewandte Mathematik und Mechanik 72 (1992) T537-T539.
[34] J. Pietraszek, N. Radek, A.V. Goroshko. Challenges for the DOE methodology related to the introduction of Industry 4.0. Production Engineering Archives 26 (2020) 190-194. https://doi.org/10.30657/pea.2020.26.33
[35] H. Danielewski, A. Skrzypczyk, W. Zowczak, D. Gontarski, L. Płonecki, H. Wiśniewski, D. Soboń, A. Kalinowski, G. Bracha, K. Borkowski. Numerical analysis of laser-welded flange pipe joints in lap and fillet configurations, Technical Transactions 118 (2021) art. e2021030. https://doi.org/10.37705/TechTrans/e2021030
[36] J. Pietraszek. Response surface methodology at irregular grids based on Voronoi scheme with neural network approximator. 6th Int. Conf. on Neural Networks and Soft Computing, Jun 11-15, 2002, Springer, 250-255. https://doi.org/10.1007/978-3-7908-1902-1_35
[37] J. Pietraszek, E. Skrzypczak-Pietraszek. The uncertainty and robustness of the principal component analysis as a tool for the dimensionality reduction. Solid State Phenom. 235 (2015) 1-8. https://doi.org/10.4028/www.scientific.net/SSP.235.1
