Maintenance of industrial reactors supported by deep learning driven ultrasound tomography

• Autorzy: Kłosowski Grzegorz , Rymarczyk Tomasz , Kania Konrad , Świć Antoni , Cieplak Tomasz

Identyfikatory

DOI

10.17531/ein.2020.1.16

Warianty tytułu

PL

Eksploatacja reaktorów przemysłowych ze wspomaganiem tomografii ultradźwiękowej i algorytmów głębokiego uczenia

• Języki publikacji: EN

Abstrakty

EN

Monitoring of industrial processes is an important element ensuring the proper maintenance of equipment and high level of processes reliability. The presented research concerns the application of the deep learning method in the field of ultrasound tomography (UST). A novel algorithm that uses simultaneously multiple classification convolutional neural networks (CNNs) to generate monochrome 2D images was developed. In order to meet a compromise between the number of the networks and the number of all possible outcomes of a single network, it was proposed to divide the output image into 4-pixel clusters. Therefore, the number of required CNNs has been reduced fourfold and there are 16 distinct outcomes from single network. The new algorithm was first verified using simulation data and then tested on real data. The accuracy of image reconstruction exceeded 95%. The results obtained by using the new CNN clustered algorithm were compared with five popular machine learning algorithms: shallow Artificial Neural Network, Linear Support Vector Machine, Classification Tree, Medium k-Nearest Neighbor classification and Naive Bayes. Based on this comparison, it was found that the newly developed method of multiple convolutional neural networks (MCNN) generates the highest quality images.

PL

Monitorowanie procesów przemysłowych jest ważnym elementem zapewniającym właściwą eksploatację urządzeń i wysoki poziom niezawodności procesów. Prezentowane badania dotyczą zastosowania metod głębokiego uczenia w obszarze eksploatacji zbiornikowych reaktorów przemysłowych. W procesach przemysłowych opartych na reakcjach chemicznych zachodzących wewnątrz procesowej tomografii ultradźwiękowej (UST). Opracowano nowatorski algorytm wykorzystujący jednocześnie wiele klasyfikacyjnych splotowych sieci neuronowych (CNN) do generowania monochromatycznych obrazów 2D. Aby osiągnąć kompromis między liczbą sieci a liczbą wszystkich możliwych wyników pojedynczej sieci, zaproponowano podział obrazu wyjściowego na klastry 4-pikselowe. W związku z tym liczba wymaganych CNN została czterokrotnie zmniejszona i istnieje 16 różnych wyników z jednej sieci. Nowy algorytm został najpierw zweryfikowany przy użyciu danych symulacyjnych, a następnie przetestowany na danych rzeczywistych. Dokładność rekonstrukcji obrazu przekroczyła 95%. Wyniki uzyskane przy użyciu nowego algorytmu klastrowego CNN zostały porównane z pięcioma popularnymi algorytmami uczenia maszynowego: płytką sztuczną siecią neuronową, maszyną liniowego wektora wsparcia, drzewem klasyfikacji, klasyfikacją średniego k-najbliższego sąsiada i naiwnym Bayesem. Na podstawie tego porównania stwierdzono, że nowo opracowana metoda wielu splotowych sieci neuronowych (MCNN) generuje obrazy o najwyższej jakości.

Słowa kluczowe

EN

deep learning; inverse problem; ultrasound tomography; image reconstruction; process tomography

PL

uczenie głębokie; problem odwrotny; tomografia ultradźwiękowa; rekonstrukcja obrazu; tomografia procesowa

• Wydawca: Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne
• Czasopismo: Eksploatacja i Niezawodność
• Rocznik: 2020
• Tom: Vol. 22, no. 1
• Strony: 138--147
• Opis fizyczny: Bibliogr. 45 poz., rys., tab.

Twórcy

autor

Kłosowski Grzegorz

• Lublin University of Technology Department of Organization of Enterprise ul. Nadbystrzycka 38D, 20-618 Lublin, Poland

autor

Rymarczyk Tomasz

• University of Economics and Innovation ul. Projektowa 4, 20-209 Lublin, Poland Research and Development Center, Netrix S.A. ul. Związkowa 26, 20-148 Lublin, Poland

autor

Kania Konrad

• University of Economics and Innovation ul. Projektowa 4, 20-209 Lublin, Poland Research and Development Center, Netrix S.A. ul. Związkowa 26, 20-148 Lublin, Poland

autor

Świć Antoni

• Lublin University of Technology Institute of Technological Systems of Information ul. Nadbystrzycka 38D, 20-618 Lublin, Poland

autor

Cieplak Tomasz

• Lublin University of Technology Department of Organization of Enterprise ul. Nadbystrzycka 38D, 20-618 Lublin, Poland

Bibliografia

• 1. Anders D, Rzasa M. The possibility of composting animal waste products. Environment Protection Engineering 2007;33(2):7-15.
• 2. Arevalo J, González FA, Ramos-Pollán R, Oliveira JL, Guevara Lopez MA. Representation learning for mammography mass lesion classification with convolutional neural networks. Computer Methods and Programs in Biomedicine 2016;127: 248-257, https://doi.org/10.1016/j.cmpb.2015.12.014.
• 3. Babout L, Grudzień K, Wiącek J, Niedostatkiewicz M, Karpiński B, Szkodo M. Selection of material for X-ray tomography analysis and DEM simulations: comparison between granular materials of biological and non-biological origins. Granular Matter 2018; 20(3): 38, https://doi.org/10.1007/s10035-018-0809-y.
• 4. Banasiak R, Wajman R, Jaworski T, Fiderek P, Fidos H, Nowakowski J, Sankowski D. Study on two-phase flow regime visualization and identification using 3D electrical capacitance tomography and fuzzy-logic classification. International Journal of Multiphase Flow 2014; 58: 1-14, https://doi.org/10.1016/j.ijmultiphaseflow.2013.07.003.
• 5. Bartusek K, Fiala P, Mikulka J. Numerical modeling of magnetic field deformation as related to susceptibility measured with an MR system. Radioengineering 2008;17(4):113-118.
• 6. Bishop CM. Pattern Recognition and Machine Learning. Springer-Verlag New York 2006.
• 7. Chen H, Ni D, Qin J, Li S, Yang X, Wang T, Heng PA. Standard Plane Localization in Fetal Ultrasound via Domain Transferred Deep Neural Networks. IEEE Journal of Biomedical and Health Informatics 2015; 19(5): 1627-1636, https://doi.org/10.1109/JBHI.2015.2425041.
• 8. Du X, Li J, Feng H, Chen S. Image reconstruction of internal defects in wood based on segmented propagation rays of stress waves. Applied Sciences (Switzerland) 2018; 8(10): 1778, https://doi.org/10.3390/app8101778.
• 9. Goetzke-Pala A, Hoła A, Sadowski Ł. A non-destructive method of the evaluation of the moisture in saline brick walls using artificial neural networks. Archives of Civil and Mechanical Engineering 2018; 18(4): 1729-1742, https://doi.org/10.1016/j.acme.2018.07.004.
• 10. Gola A, Kłosowski G. Application of Fuzzy Logic and Genetic Algorithms in Automated Works Transport Organization. In: Advances in Intelligent Systems and Computing. Vol 620. Springer, Cham 2018: 29-36, https://doi.org/10.1007/978-3-319-62410-5_4.
• 11. Khairi MTM, Ibrahim S, Yunus MAM, Faramarzi M, Sean GP, Pusppanathan J, Abid A. Ultrasound computed tomography for material inspection: Principles, design and applications. Measurement 2019; 146: 490-523, https://doi.org/10.1016/j.measurement.2019.06.053.
• 12. Kłosowski G, Kozłowski E, Gola A. Integer Linear Programming in Optimization of Waste After Cutting in the Furniture Manufacturing. In: Burduk A., Mazurkiewicz D. (Eds) Intelligent Systems in Production Engineering and Maintenance - ISPEM 2017, vol 637, 2018: 260-270, https://doi.org/10.1007/978-3-319-64465-3_26.
• 13. Kłosowski G, Rymarczyk T, Gola A. Increasing the reliability of flood embankments with neural imaging method. Applied Sciences 2018; 8(9): 1457, https://doi.org/10.3390/app8091457.
• 14. Kozłowski E., Mazurkiewicz D., Kowalska B., Kowalski D. – Binary Linear Programming as a Decision-Making Aid for Water Intake Operators. In book: Intelligent Systems in Production Engineering and Maintenance – ISPEM 2017, Edition: Advances in Intelligent Systems and Computing vol. 637. Publisher: Springer International Publishing, Editors: Anna Burduk, Dariusz Mazurkiewicz, pp.199-208, DOI: 10.1007/978-3-319-64465-3_20.
• 15. Krawczyk A, Korzeniewska E. Magnetophosphenes - history and contemporary implications. Przegląd Elektrotechniczny 2018; 1(1): 63-66, https://doi.org/10.15199/48.2018.01.16.
• 16. Kryszyn J, Smolik W. Toolbox for 3D modelling and image reconstruction in electrical capacitance tomography. Informatics Control Measurement in Economy and Environment Protection 2017; 7(1): 137-145, https://doi.org/10.5604/01.3001.0010.4603.
• 17. Kryszyn J, Wanta DM, Smolik WT. Gain Adjustment for Signal-to-Noise Ratio Improvement in Electrical Capacitance Tomography System EVT4. IEEE Sensors Journal 2017; 17(24): 8107-8116, https://doi.org/10.1109/JSEN.2017.2744985.
• 18. Lei J, Liu Q, Wang X. Deep Learning-Based Inversion Method for Imaging Problems in Electrical Capacitance Tomography. IEEE Transactions on Instrumentation and Measurement 2018; 67(9): 2107-2118, https://doi.org/10.1109/TIM.2018.2811228.
• 19. Li X, Li J, He D, Qu Y. Gear pitting fault diagnosis using raw acoustic emission signal based on deep learning. Eksploatacja i Niezawodnosc - Maintenance and Reliability 2019; 21(3): 403-410, https://doi.org/10.17531/ein.2019.3.6.
• 20. Lopato P, Chady T, Sikora R, Gratkowski S, Ziolkowski M. Full wave numerical modelling of terahertz systems for nondestructive evaluation of dielectric structures. COMPEL - The international journal for computation and mathematics in electrical and electronic engineering 2013; 32(3): 736-749, https://doi.org/10.1108/03321641311305719.
• 21. Ma J, Wu F, Zhu J, Xu D, Kong D. A pre-trained convolutional neural network based method for thyroid nodule diagnosis. Ultrasonics 2017; 73: 221-230, https://doi.org/10.1016/j.ultras.2016.09.011.
• 22. Majchrowicz M, Kapusta P, Jackowska-Strumiłło L, Sankowski D. Acceleration of image reconstruction process in the electrical capacitance tomography 3D in heterogeneous, multi-GPU system. Informatics Control Measurement in Economy and Environment Protection 2017; 7(1): 37-41, https://doi.org/10.5604/01.3001.0010.4579.
• 23. Mikulka J. GPU-Accelerated Reconstruction of T2 Maps in Magnetic Resonance Imaging. Measurement Science Review 2015; 15(4): 210-218, https://doi.org/10.1515/msr-2015-0029.
• 24. Podgórni E, Rząsa M. Investigation of the effects of salinity and temperature on the removal of iron from water by aeration, filtration, and coagulation. Polish Journal of Environmental Studies 2014; 23(6): 2157-2161, https://doi.org/10.15244/pjoes/24927.
• 25. Psuj G. Multi-Sensor Data Integration Using Deep Learning for Characterization of Defects in Steel Elements. Sensors 2018; 18(2): 292. https://doi.org/10.3390/s18010292.
• 26. Qayyum A, Anwar SM, Awais M, Majid M. Medical image retrieval using deep convolutional neural network. Neurocomputing 2017; 266: 8-20, https://doi.org/10.1016/j.neucom.2017.05.025.
• 27. Romanowski A. Big Data-Driven Contextual Processing Methods for Electrical Capacitance Tomography. IEEE Transactions on Industrial Informatics 2019; 15(3): 1609-1618, https://doi.org/10.1109/TII.2018.2855200.
• 28. Romanowski A. Contextual Processing of Electrical Capacitance Tomography Measurement Data for Temporal Modeling of Pneumatic Conveying Process. In: 2018 Federated Conference on Computer Science and Information Systems (FedCSIS) 2018: 283-286, https://doi.org/10.15439/2018F171.
• 29. Romanowski A, Łuczak P, Grudzień K. X-ray Imaging Analysis of Silo Flow Parameters Based on Trace Particles Using Targeted Crowdsourcing. Sensors 2019; 19(15): 3317, https://doi.org/10.3390/s19153317.
• 30. Rymarczyk T. New methods to determine moisture areas by electrical impedance tomography. Kojima F, Kobayashi F, Nakamoto H, eds. International Journal of Applied Electromagnetics and Mechanics 2016; 52(1-2): 79-87, https://doi.org/10.3233/JAE-162071.
• 31. Rymarczyk T. Using electrical impedance tomography to monitoring flood banks. In: International Journal of Applied Electromagnetics and Mechanics 2014; 45: 489-494, https://doi.org/10.3233/JAE-141868
• 32. Rymarczyk T, Adamkiewicz P, Duda K, Szumowski J, Sikora J. New electrical tomographic method to determine dampness in historical buildings. Archives of Electrical Engineering 2016; 65(2): 273-283, https://doi.org/10.1515/aee-2016-0019.
• 33. Rymarczyk T, Kłosowski G, Cieplak T, Kozłowski E, Kania K. Application of a regressive neural network with autoencoder for monochromatic images in ultrasound tomography. In: Institute of Electrical and Electronics Engineers (IEEE) 2019: 156-160, https://doi.org/10.23919/PTZE.2019.8781750.
• 34. Rząsa MR. A new transducer of double processing for capacitive tomography. Metrology and Measurement Systems 2007; 14(2): 291-305.
• 35. Rząsa MR, Dobrowolski B. The prototype capacitance tomography sensor with increased sensitivity near the wall. Journal of Energy Science 2010; 1(1):133-145.
• 36. Sezer A, Basri Sezer H. Convolutional neural network based diagnosis of bone pathologies of proximal humerus. Neurocomputing 2019, https://doi.org/10.1016/j.neucom.2018.11.115.
• 37. Shahdoosti HR, Rahemi Z. Edge-preserving image denoising using a deep convolutional neural network. Signal Processing 2019; 159: 20-32, https://doi.org/10.1016/j.sigpro.2019.01.017.
• 38. Świderski A, Jóźwiak A, Jachimowski R. Operational quality measures of vehicles applied for the transport services evaluation using artificial neural networks. Eksploatacja i Niezawodnosc - Maintenance and Reliability 2018; 20(2): 292-299, https://doi.org/10.17531/ein.2018.2.16.
• 39. Szczesny A, Korzeniewska E. Selection of the method for the earthing resistance measurement. Przegląd Elektrotechniczny 2018; 94(12):178-181.
• 40. Vališ D, Forbelská M, Vintr Z, Hasilová K, Leuchter J. Platinum thermometer failure estimation based on dynamic linear models. Engineering Failure Analysis 2019; 101: 418-435, https://doi.org/10.1016/j.engfailanal.2019.03.024.
• 41. Vališ D, Mazurkiewicz D. Application of selected Levy processes for degradation modelling of long range mine belt using real-time data. Archives of Civil and Mechanical Engineering 2018; 18(4): 1430-1440, https://doi.org/10.1016/j.acme.2018.05.006.
• 42. Wajman R, Fiderek P, Fidos H, Jaworski T, Nowakowski J, Sankowski D, Banasiak R. Metrological evaluation of a 3D electrical capacitance tomography measurement system for two-phase flow fraction determination. Measurement Science and Technology 2013; 24(6): 065302, https://doi.org/10.1088/0957-0233/24/6/065302.
• 43. Zhang Q, Xiao Y, Dai W, Suo J, Wang C, Shi J, Zheng H. Deep learning based classification of breast tumors with shear-wave elastography. Ultrasonics 2016; 72: 150-157, https://doi.org/10.1016/j.ultras.2016.08.004.
• 44. Zhao R, Yan R, Chen Z, Mao K, Wang P, Gao RX. Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing 2019; 115: 213-237, https://doi.org/10.1016/j.ymssp.2018.05.050.
• 45. Ziolkowski M, Gratkowski S, Zywica AR. Analytical and numerical models of the magnetoacoustic tomography with magnetic induction. COMPEL - The International Journal for Computation and Mathematics in Electrical and Electronic Engineering 2018; 37(2): 538-548, https://doi.org/10.1108/COMPEL-12-2016-0530.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).