scholarly journals Acceleration of image reconstruction in 3D Electrical Capacitance Tomography in heterogeneous, multi-GPU system using sparse matrix computations and Finite Element Method

2016 ◽  
Author(s):  
Paweł Kapusta ◽  
Michał Majchrowicz ◽  
Dominik Sankowski ◽  
Lidia Jackowska-Strumiłło
Keyword(s):  
Finite Element Method ◽  
Finite Element ◽  
Image Reconstruction ◽  
Sparse Matrix ◽  
Electrical Capacitance Tomography ◽  
Electrical Capacitance ◽  
Matrix Computations ◽  
Capacitance Tomography ◽  
Element Method

Sensor Modeling For An Electrical Capacitance Tomography System Using Comsol Multiphysics

2012 ◽  
Author(s):  
Muhammad Afiq Zimam ◽  
Elmy Johana Mohamad ◽  
Ruzairi Abdul Rahim ◽  
Leow Pei Ling
Keyword(s):  
Finite Element Method ◽  
Finite Element ◽  
Comsol Multiphysics ◽  
Electrical Capacitance Tomography ◽  
Electrical Capacitance ◽  
Tomography System ◽  
Physical Sensors ◽  
Capacitance Tomography ◽  
Sensor Modeling ◽  
Element Method

Kerja penyelidikan ini membentangkan proses pembinaan model bagi Pengesan Kapasitan Elektrik Tomografi (ECT) menggunakan Perisian Kaedah Elemen Terhingga (Finite Element method–FEM) COMSOL Multiphysics. Meskipun pengesan fizikal adalah dalam bentuk tiga dimensi (3D) tetapi secara amnya sering dimodelkan secara kepingan/ keratan rentas dalam bentuk dua dimensi (2D). Projek ini menunjukkan pendekatan model dalam bentuk geometri 3D dan 2D, linear FEM menggunakan perisian COMSOL Multiphysics dibina adalah untuk mendapatkan nilai kapasitor di antara elektrod apabila medan elektrik dikenakan dan untuk melihat bagaimana pengagihan permittivity di dalam paip yang bertutup menerusi pengesan. Bayang–bayang yang direkacipta dan nilai–nilai diukur dikemukakan dalam bentuk paip yg kosong dan aliran anulus. Model ECT adalah mewakili perkakasan yang sedia ada, ECT mudah alih yang telah dibina oleh Kumpulan Penyelidikan PROTOM UTM. Kata kunci: Pengesan; model; ECT; COMSOL multiphysics This work presents the development process for modeling an ECT (Electrical Capacitance Tomography) sensor using FEM software package COMSOL Multiphysics. The physical sensors are 3D dimensional but it has been common to model the slice or the cross–section in 2D. This project shows the modeling approach for 2D and 3D geometries, the linear Finite Element method (FEM) using COMSOL Multiphysics is developed in order to obtain the capacitance between electrodes when an electric field is applied and to obtain the permittivity distribution inside the closed pipe from the sensor. Generated phantoms and measured values are presented for empty and annular pattern. Simulation is verified using phantoms inside the 16 electrode sensor. The ECT model is representative by existing hardware, Portable ECT, PROTOM Research Group UTM. Key words: Sensor; modeling; ECT; COMSOL multiphysics

Application of GPU Parallel Computing for Acceleration of Finite Element Method Based 3D Reconstruction Algorithms in Electrical Capacitance Tomography

2012 ◽  
Vol 17 (4) ◽  
pp. 339-346 ◽  
Author(s):  
Paweł Kapusta ◽  
Michał Majchrowicz ◽  
Dominik Sankowski ◽  
Robert Banasiak
Keyword(s):  
Finite Element Method ◽  
Finite Element ◽  
Parallel Computing ◽  
Graphics Processing Units ◽  
Sparse Matrices ◽  
Electrical Capacitance Tomography ◽  
Electrical Capacitance ◽  
Reconstruction Algorithms ◽  
Capacitance Tomography ◽  
Element Method

Abstract With the increasing complexity and scale of industrial processes their visualization is becoming increasingly important. Especially popular are non-invasive methods, which do not interfere directly with the process. One of them is the 3D Electrical Capacitance Tomography. It possesses however a serious flaw - in order to obtain a fast and accurate visualization requires application of computationally intensive algorithms. Especially non-linear reconstruction using Finite Element Method is a multistage, complex numerical task, requiring many linear algebra transformations on very large data sets. Such process, using traditional CPUs can take, depending on the used meshes, up to several hours. Consequently it is necessary to develop new solutions utilizing GPGPU (General Purpose Computations on Graphics Processing Units) techniques to accelerate the reconstruction algorithm. With the developed hybrid parallel computing architecture, based on sparse matrices, it is possible to perform tomographic calculations much faster using GPU and CPU simultaneously, both with Nvidia CUDA and OpenCL.

scholarly journals A Benchmark Dataset and Deep Learning-Based Image Reconstruction for Electrical Capacitance Tomography

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3701 ◽  
Author(s):  
Jin Zheng ◽  
Jinku Li ◽  
Yi Li ◽  
Lihui Peng
Keyword(s):  
Machine Learning ◽  
Image Reconstruction ◽  
Benchmark Dataset ◽  
Electrical Capacitance Tomography ◽  
Electrical Capacitance ◽  
Reconstruction Algorithms ◽  
Reconstruction Methods ◽  
Image Reconstruction Algorithms ◽  
Capacitance Tomography ◽  
The Relationship

Electrical Capacitance Tomography (ECT) image reconstruction has developed for decades and made great achievements, but there is still a need to find a new theoretical framework to make it better and faster. In recent years, machine learning theory has been introduced in the ECT area to solve the image reconstruction problem. However, there is still no public benchmark dataset in the ECT field for the training and testing of machine learning-based image reconstruction algorithms. On the other hand, a public benchmark dataset can provide a standard framework to evaluate and compare the results of different image reconstruction methods. In this paper, a benchmark dataset for ECT image reconstruction is presented. Like the great contribution of ImageNet that transformed machine learning research, this benchmark dataset is hoped to be helpful for society to investigate new image reconstruction algorithms since the relationship between permittivity distribution and capacitance can be better mapped. In addition, different machine learning-based image reconstruction algorithms can be trained and tested by the unified dataset, and the results can be evaluated and compared under the same standard, thus, making the ECT image reconstruction study more open and causing a breakthrough.

Sign in / Sign up

Export Citation Format

Share Document