Electrical impedance tomography in 3D flood embankments testing

Abstract

The article presents non-destructive testing based on electrical impedance tomography (EIT) for spatial (3D) monitoring of flood embankments. Therefore, to solve the inverse problem of the EIT, an effective algorithm based on multiple elastic nets has been developed. The originality of the solution is based on the application of many elastic net algorithms as functions, each of which, based on the vector of all measurements, generates the value of a single pixel for the reconstructed image. In this way, the set of elastic nets is equal to the resolution of the image output. Such an approach, although requiring more computing power, yields high resolution images. In addition, the presented algorithms are characterized by high noise immunity and distortion of measurement data. Five different electrode systems were tested in the samples and compared with each other in two measurement variants (stimulations). A reconstruction made on the basis of actual measurements obtained from the physical model was also presented.

The presented solution provides a visual analysis of seepages and leaks, which allows for quick and effective intervention and possible prevention of dangers. The research proved that the use of tomographic measurement techniques in combination with the image reconstruction algorithm based on elastic net allows for non-invasive and very accurate spatial assessment of leaks and damages of flood embankments. The received results confirm the effectiveness of the presented research.

Keywords

Electrical impedance tomography machine learning flood embankment elastic net

Get full access to this article

View all access options for this article.

References

Adler

Lionheart

WRB

(2006) Uses and abuses of EIDORS: An extensible software base for EIT. Physiological Measurement 27(5): S25–S42.

Babout

, et al. (2018) Selection of material for X-ray tomography analysis and DEM simulations: comparison between granular materials of biological and non-biological origins. Granular Matter 20(3): 38.

Banasiak

, et al. (2014) Study on two-phase flow regime visualization and identification using 3D electrical capacitance tomography and fuzzy-logic classification. International Journal of Multiphase Flow 58: 1–14.

Duraj

Korzeniewska

Krawczyk

(2015) Classification algorithms to identify changes in resistance. Przegląd Elektrotechniczny 1(12): 82–84.

Dusek

Hladky

Mikulka

(2017) Electrical impedance tomography methods and algorithms processed with a GPU. In: 2017 Progress In Electromagnetics Research Symposium - Spring (PIERS), St. Petersburg, Russia, 22–25 May 2017, pp. 1710–1714. IEEE.

Goetzke-Pala

Hoła

Sadowski

(2018) A non-destructive method of the evaluation of the moisture in saline brick walls using artificial neural networks. Archives of Civil and Mechanical Engineering 18(4): 729–1742.

Grudzien

, et al. (2016) Application of twin-plane ECT sensor for identification of the internal imperfections inside concrete beams. In: IEEE International Instrumentation and Measurement Technology Conference Proceedings, Taipei, Taiwan, 23–26 May 2016, pp. 1–6. IEEE.

Hastie

Tibshirani

Friedman

(2009) The Elements of Statistical Learning: Data Mining, Inference, and Prediction. New York: Springer.

Kozłowski

, et al. (2018) Binary Linear programming as a decision-making aid for water intake operators. In: Burduk

Mazurkiewicz

(eds) Intelligent Systems in Production Engineering and Maintenance–ISPEM 2017. Advances in Intelligent Systems and Computing, vol 637. Cham: Springer, pp. 199–208.

10.

Kłosowski

Rymarczyk

Gola

(2018) Increasing the reliability of flood embankments with neural imaging method. Applied Sciences 8(9): 1457.

11.

Kryszyn

, et al. (2017a) Architecture of EVT4 data acquisition system for electrical capacitance tomography. Measurement 101: 28–39.

12.

Kryszyn

, et al. (2017b) Development of electrical capacitance tomograph design in the nuclear and medical electronics division. Informatics Control Measurement in Economy and Environment Protection 7(1): 111–114.

13.

Majchrowicz

, et al. (2017) Acceleration of image reconstruction process in the electrical capacitance tomography 3d in heterogeneous, multi-gpu system. Informatics Control Measurement in Economy and Environment Protection 7(1): 37–41.

14.

Romanowski

(2018a) Big Data-driven contextual processing methods for electrical capacitance tomography. IEEE Transactions on Industrial Informatics 15(3): 1609–1618.

15.

Romanowski

(2018b) 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), 9–12 September 2018, pp. 283–286.

16.

Rymarczyk

Kłosowski

(2018a) Application of neural reconstruction of tomographic images in the problem of reliability of flood protection facilities. Eksploatacja i Niezawodnosc – Maintenance and Reliability 20(3): 425–434.

17.

Rymarczyk

Kłosowski

(2018b) Applying machine learning algorithms to solve inverse problems in electrical tomography. In: Mastorakis

Mladenov

Bulucea

(eds), MATEC Web of Conferences vol 210, article 02016.

18.

Rymarczyk

Kłosowski

Kozłowski

(2018) A Non-destructive system based on electrical tomography and machine learning to analyze the moisture of buildings. Sensors 18(7): 2285.

19.

Sentenac

, et al. (2017) Post flooding damage assessment of earth dams and historical reservoirs using non-invasive geophysical techniques. Journal of Applied Geophysics 146: 138–148.

20.

Soleimani

, et al. (2009) Four-dimensional electrical capacitance tomography imaging using experimental data. Progress In Electromagnetics Research 90: 171–186.

21.

Tibshirani

(1996) Regression Shrinkage and selection via the lasso. Journal of the Royal Statistical Society. Series B (Methodological) 58(1): 267–288.

22.

Tong

Liu

(2019) Computationally efficient image reconstruction algorithm for electrical capacitance tomography. Transactions of the Institute of Measurement and Control 41(3): 631–646.

23.

Vališ

Mazurkiewicz

(2018) Application of selected Levy processes for degradation modelling of long range mine belt using real-time data. Archives of Civil and Mechanical Engineering 18(4): 1430–1440.

24.

Vališ

Mazurkiewicz

Forbelska

(2017) Modelling of a transport belt degradation using state space model. In: 2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), Singapore, Singapore, 10–13 December 2017, pp. 949–953. IEEE.

25.

Wajman

, et al. (2013) Metrological evaluation of a 3D electrical capacitance tomography measurement system for two-phase flow fraction determination. Measurement Science and Technology 24(6): 065302.

26.

Wang

(2015) Industrial Tomography: Systems and Applications. Sawston, Cambridge: Elsevier Ltd. Woodhead Publishing.

27.

Yeboah-Forson

Comas

Whitman

(2014) Integration of electrical resistivity imaging and ground penetrating radar to investigate solution features in the Biscayne Aquifer. Journal of Hydrology 515: 129–138.

28.

Ziolkowski

Gratkowski

Zywica

(2018) Analytical and numerical models of the magnetoacoustic tomography with magnetic induction. COMPEL - The International Journal for Computation and Mathematics in Electrical and Electronic Engineering 37(2): 538–548.

29.

Zou

Hastie

(2005) Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 67(2): 301–320.

Electrical impedance tomography in 3D flood embankments testing – elastic net approach

Abstract

Keywords

Get full access to this article

References