Selection of material for X-ray tomography analysis and DEM simulations: comparison between granular materials of biological and non-biological origins

et al. 2019

Sensors

The main goal of this work was to compare the selected machine learning methods with the classic deterministic method in the industrial field of electrical impedance tomography. The research focused on the development and comparison of algorithms and models for the analysis and reconstruction of data using electrical tomography. The novelty was the use of original machine learning algorithms. Their characteristic feature is the use of many separately trained subsystems, each of which generates a single pixel of the output image. Artificial Neural Network (ANN), LARS and Elastic net methods were used to solve the inverse problem. These algorithms have been modified by a corresponding increase in equations (multiply) for electrical impedance tomography using the finite element method grid. The Gauss-Newton method was used as a reference to machine learning methods. The algorithms were trained using learning data obtained through computer simulation based on real models. The results of the experiments showed that in the considered cases the best quality of reconstructions was achieved by ANN. At the same time, ANN was the slowest in terms of both the training process and the speed of image generation. Other machine learning methods were comparable with the deterministic Gauss-Newton method and with each other.

Section: Methodsmentioning

confidence: 99%

Comparison of Selected Machine Learning Algorithms for Industrial Electrical Tomography

et al. 2019

Sensors

“…There are many optimization methods (Babout et al, 2018;Goetzke-Pala et al, 2018;K1osowski et al, 2018a,b;Valisˇand Mazurkiewicz, 2018;Valisˇet al, 2017;Wajman et al, 2013;Ziolkowski et al, 2018). In this article, the authors focused on the application of elastic net which is one of the machine learning algorithms (Rymarczyk and K1osowski, 2018b).…”

Section: The Methodsmentioning

confidence: 99%

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

Transactions of the Institute of Measurement and Control

2019

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.

“…The physical source of data may be electricity, magnetism, sound waves, electromagnetic waves, X-rays, visible light, etc. The most common types of tomography used in industrial processes and medicine are: electrical impedance tomography (EIT) [10,11,12], computed tomography (CT) [13], radio tomographic imaging (RTI) [14], electrical capacitance tomography (ECT) [15,16,17,18,19,20] and ultrasound transmission tomography (UST) [21].…”

Section: Introductionmentioning

confidence: 99%

Logistic Regression for Machine Learning in Process Tomography

et al. 2019

Sensors

117

The main goal of the research presented in this paper was to develop a refined machine learning algorithm for industrial tomography applications. The article presents algorithms based on logistic regression in relation to image reconstruction using electrical impedance tomography (EIT) and ultrasound transmission tomography (UST). The test object was a tank filled with water in which reconstructed objects were placed. For both EIT and UST, a novel approach was used in which each pixel of the output image was reconstructed by a separately trained prediction system. Therefore, it was necessary to use many predictive systems whose number corresponds to the number of pixels of the output image. Thanks to this approach the under-completed problem was changed to an over-completed one. To reduce the number of predictors in logistic regression by removing irrelevant and mutually correlated entries, the elastic net method was used. The developed algorithm that reconstructs images pixel-by-pixel is insensitive to the shape, number and position of the reconstructed objects. In order to assess the quality of mappings obtained thanks to the new algorithm, appropriate metrics were used: compatibility ratio (CR) and relative error (RE). The obtained results enabled the assessment of the usefulness of logistic regression in the reconstruction of EIT and UST images.