The use of elastic net and neural networks in industrial process tomography

The article presents an innovative approach based on electrical capacitance tomography (ECT) improving industrial tomography processes. Thanks to the application of elastic net and artificial neural networks, algorithms have been developed that enable obtaining high quality images and resolutions. During the experiments, two methods of reconstructing "pixel by pixel" images were compared. Both methods showed high efficiency, and the use of elastic net accelerated the operation of the ECT system. Streszczenie. W artykule przedstawiono nowatorskie podejście oparte na ECT usprawniające procesy tomografii przemysłowej. Dzięki zastosowaniu elastic net i sztucznych sieci neuronowych opracowano algorytmy umożliwiające uzyskanie obrazów o wysokiej jakości i rozdzielczości. W trakcie przeprowadzonych eksperymentów porównano dwie metody rekonstrukcji obrazów "pixel by pixel". Obie metody wykazały się wysoką skutecznością, a wykorzystanie elastic net przyspieszyło działanie systemu ECT. (Zastosowanie elastic net i sieci neuronowych w tomografii przemysłowej).

[1]  T. Rymarczyk,et al.  Measurement Methods and Image Reconstruction in Electrical Impedance Tomography , 2012 .

[2]  Tomasz Rymarczyk,et al.  A Non-Destructive System Based on Electrical Tomography and Machine Learning to Analyze the Moisture of Buildings , 2018, Sensors.

[3]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[4]  Jacek Kryszyn,et al.  Toolbox for 3D modelling and image reconstruction in electrical capacitance tomography , 2017 .

[5]  Arkadiusz Gola,et al.  Integer Linear Programming in Optimization of Waste After Cutting in the Furniture Manufacturing , 2017 .

[6]  Dariusz Mazurkiewicz.  Maintenance of belt conveyors using an expert system based on fuzzy logic , 2015 .

[7]  Andrzej Romanowski,et al.  Application of electrical capacitance tomography and artificial neural networks to rapid estimation of cylindrical shape parameters of industrial flow structure , 2016 .

[8]  Robert Banasiak,et al.  Metrological evaluation of a 3D electrical capacitance tomography measurement system for two-phase flow fraction determination , 2013 .

[9]  Dominik Sankowski,et al.  Application of twin-plane ECT sensor for identification of the internal imperfections inside concrete beams , 2016, 2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings.

[10]  Przemyslaw Lopato,et al.  Full wave numerical modelling of terahertz systems for nondestructive evaluation of dielectric structures , 2013 .

[11]  Grzegorz Psuj.  Multi-Sensor Data Integration Using Deep Learning for Characterization of Defects in Steel Elements † , 2018, Sensors.

[12]  Jacek Kryszyn,et al.  Gain Adjustment for Signal-to-Noise Ratio Improvement in Electrical Capacitance Tomography System EVT4 , 2017, IEEE Sensors Journal.

[13]  Rahim Alhamzawi,et al.  The Bayesian adaptive lasso regression. , 2018, Mathematical biosciences.

[14]  Marcin Ziolkowski,et al.  Analytical and numerical models of the magnetoacoustic tomography with magnetic induction , 2018 .

[15]  Tomasz Rymarczyk,et al.  Applying industrial tomography to control and optimization flow systems , 2018, Open Physics.

[16]  Tomasz Rymarczyk,et al.  Application of neural reconstruction of tomographic images in the problem of reliability of flood protection facilities , 2018, Eksploatacja i Niezawodnosc - Maintenance and Reliability.

[17]  J. Mikulka,et al.  Electrical impedance tomography methods and algorithms processed with a GPU , 2017, 2017 Progress In Electromagnetics Research Symposium - Spring (PIERS).