ECT-LSTM-RNN: An Electrical Capacitance Tomography Model-Based Long Short-Term Memory Recurrent Neural Networks for Conductive Materials
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 capacitanc...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9429218/ |
| _version_ | 1818646999986077696 |
|---|---|
| author | Wael Deabes Alaa Sheta Malik Braik |
| author_facet | Wael Deabes Alaa Sheta Malik Braik |
| author_sort | Wael Deabes |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-17T00:55:34Z |
| format | Article |
| id | doaj.art-12d7ddb7efeb4f4bb06768f89a57f899 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T00:55:34Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-12d7ddb7efeb4f4bb06768f89a57f8992022-12-21T22:09:37ZengIEEEIEEE Access2169-35362021-01-019763257633910.1109/ACCESS.2021.30794479429218ECT-LSTM-RNN: An Electrical Capacitance Tomography Model-Based Long Short-Term Memory Recurrent Neural Networks for Conductive MaterialsWael Deabes0https://orcid.org/0000-0002-1814-2643Alaa Sheta1https://orcid.org/0000-0002-3727-6276Malik Braik2Department of Computer Science in Jamoum, Umm Al-Qura University, Makkah, Saudi ArabiaDepartment of Computer Science, Southern Connecticut State University, New Haven, CT, USADepartment of Computer Science, Al-Balqa Applied University, Al-Salt, JordanImage 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.https://ieeexplore.ieee.org/document/9429218/Image reconstructionlong short-term memory recurrent neural networklost foam castingmetal filling process |
| spellingShingle | Wael Deabes Alaa Sheta Malik Braik ECT-LSTM-RNN: An Electrical Capacitance Tomography Model-Based Long Short-Term Memory Recurrent Neural Networks for Conductive Materials IEEE Access Image reconstruction long short-term memory recurrent neural network lost foam casting metal filling process |
| title | ECT-LSTM-RNN: An Electrical Capacitance Tomography Model-Based Long Short-Term Memory Recurrent Neural Networks for Conductive Materials |
| title_full | ECT-LSTM-RNN: An Electrical Capacitance Tomography Model-Based Long Short-Term Memory Recurrent Neural Networks for Conductive Materials |
| title_fullStr | ECT-LSTM-RNN: An Electrical Capacitance Tomography Model-Based Long Short-Term Memory Recurrent Neural Networks for Conductive Materials |
| title_full_unstemmed | ECT-LSTM-RNN: An Electrical Capacitance Tomography Model-Based Long Short-Term Memory Recurrent Neural Networks for Conductive Materials |
| title_short | ECT-LSTM-RNN: An Electrical Capacitance Tomography Model-Based Long Short-Term Memory Recurrent Neural Networks for Conductive Materials |
| title_sort | ect lstm rnn an electrical capacitance tomography model based long short term memory recurrent neural networks for conductive materials |
| topic | Image reconstruction long short-term memory recurrent neural network lost foam casting metal filling process |
| url | https://ieeexplore.ieee.org/document/9429218/ |
| work_keys_str_mv | AT waeldeabes ectlstmrnnanelectricalcapacitancetomographymodelbasedlongshorttermmemoryrecurrentneuralnetworksforconductivematerials AT alaasheta ectlstmrnnanelectricalcapacitancetomographymodelbasedlongshorttermmemoryrecurrentneuralnetworksforconductivematerials AT malikbraik ectlstmrnnanelectricalcapacitancetomographymodelbasedlongshorttermmemoryrecurrentneuralnetworksforconductivematerials |