Novel Iterative Image Reconstruction Algorithm for Electrical Capacitance Tomography: Directional Algebraic Reconstruction Technique

Kim, Ji Hoon; Choi, Bong-Yeol; Kim, Kyung Youn

doi:10.1093/ietfec/e89-a.6.1578

Cited by 18 publications

(10 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the images reconstructed using the LBP method are often deformed, this algorithm remains the most widely used one due to its simplicity and rapidity. Iterative algorithms such as Landweber's iteration method [19] and algebraic reconstruction technique [20] can create significantly better images than can non-iterative reconstruction algorithms. Iterative image reconstruction methods during the practicality require long reconstruction time.…”

Section: A Literature Reviewmentioning

confidence: 99%

ECT-LSTM-RNN: An Electrical Capacitance Tomography Model-Based Long Short-Term Memory Recurrent Neural Networks for Conductive Materials

2021

View full text Add to dashboard Cite

Image reconstruction for industrial applications based on Electrical Capacitance Tomography (ECT) has been broadly applied. The goal of image reconstruction based ECT is to locate the distribution of permittivity for the dielectric substances along the cross-section based on the collected capacitance data. In the ECT-based image reconstruction process: (1) the relationship between capacitance measurements and permittivity distribution is nonlinear, (2) the capacitance measurements collected during image reconstruction are inadequate due to the limited number of electrodes, and (3) the reconstruction process is subject to noise leading to an ill-posed problem. Thence, constructing an accurate algorithm for real images is critical to overcoming such restrictions. This paper presents novel image reconstruction methods using Deep Learning for solving the forward and inverse problems of the ECT system for generating high-quality images of conductive materials in the Lost Foam Casting (LFC) process. Here, Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) models were implemented to predict the distribution of metal filling for the LFC process-based ECT. The recurrent connection and the gating mechanism of the LSTM is capable of extracting the contextual information that is repeatedly passing through the neural network while filtering out the noise caused by adverse factors. Experimental results showed that the presented ECT-LSTM-RNN model is highly reliable for industrial applications and can be utilized for other manufacturing processes.

show abstract

Section: A Literature Reviewmentioning

confidence: 99%

ECT-LSTM-RNN: An Electrical Capacitance Tomography Model-Based Long Short-Term Memory Recurrent Neural Networks for Conductive Materials

2021

View full text Add to dashboard Cite

show abstract

“…This back projection is conceptually very simple and straightforward; however, many assumptions are engaged in the algorithm, and in fact the image reconstruction performance may not be so plausible. To improve the image quality some modifications of the sensitivity matrix have been suggested (Kim, Choi, & Kim, 2006;Reinecke & Mewes, 1997;Villares et al, 2012).…”

Section: Image Reconstruction Based On Transmission Tomography Algorimentioning

confidence: 99%

“…For the solution of the governing equation with the boundary conditions, the constraints, and the complete electrode model, usually, the finite element method is preferred since it can easily handle the pixel-wise conductivity distribution (Brenner & Scott, 1994;Hinton & Owen, 1979;Vauhkonen 1997). The finite element formulation is well established, and many references and computer programs are available (Adler et al, 2009;Kim, Choi, & Kim, 2006;Vauhkonen, 1997). One of the most common approaches used to solve the above nonlinear least squares problems is the GausseNewton algorithm.…”

Section: Gradient-based Algorithmsmentioning

confidence: 99%

“…For the dynamic imaging, the Kalman filter algorithm and its variants are plausible (Khambampati, Rashid, Kim, Soleimani, & Kim, 2009;Kim et al, 2001Kim et al, , 2006Trigo, Gonzalez-Lima, & Amato, 2004;Vauhkonen, Karjalainen, & Kaipio, 1998). The Kalman filter well known in the control theory was devised to estimate the state of a discrete-time-controlled process governed by the linear stochastic difference equation with measurements.…”

Section: Dynamic Algorithmsmentioning

confidence: 99%

“…The Kalman filter well known in the control theory was devised to estimate the state of a discrete-time-controlled process governed by the linear stochastic difference equation with measurements. The Kalman filter provides a recursive procedure to estimate the state based on the previous states and the measurements (Kim et al, , 2006. In the sense of dynamic process, the conductivity (or permittivity) is considered as a state variable and evolving with time.…”

Section: Dynamic Algorithmsmentioning

confidence: 99%

See 2 more Smart Citations