Big Data driven U-Net based Electrical Capacitance Image Reconstruction Algorithm

Yang, Xinmeng; Zhao, Ce Zhou; Chen, Bing; Zhang, Maomao; Li, Yang

doi:10.1109/ist48021.2019.9010423

Cited by 12 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering that the reconstruction is an impedance distribution map, the evaluation indicators of image reconstruction quality were applied to evaluate the reconstruction quality of the impedance distribution map . Relative image error (RIE) and image correlation coefficient (ICC) are general indicators that are used to evaluate the quality of image reconstruction. − Similarly, these two indicators, RIE and ICC, were used to evaluate the reconstruction quality of the impedance distribution map. RIE and ICC were defined as follows where Y ′ = [ y 1 ′ , y 2 ′ , ..., y l ′ ] represents the impedance distribution data of gold standard, Y * = [ y 1 * , y 2 * , ..., y l * ] is the impedance distribution reconstruction data (predicted value), and Y ̅* and Y ̅′ are the mean values of Y * and Y ′, respectively.…”

Section: Materials and Methodsmentioning

confidence: 99%

Hydrogel Pressure Distribution Sensors Based on an Imaging Strategy and Machine Learning

Liu

Zhang

Yang

et al. 2021

ACS Appl. Electron. Mater.

View full text Add to dashboard Cite

A flexible hydrogel pressure distribution sensor has promising application prospects. However, the current hydrogel pressure distribution sensors are based on an array-type structure with complicated wires and extremely low resolution, which greatly reduce the flexibility of hydrogel and limit their applications. To overcome these limitations, we proposed and designed a hydrogel pressure distribution sensor that is able to obtain pressure distribution inside a whole piece of hydrogel. This is specifically done by arranging electrodes only around the hydrogel, which employs the strategy of electrical impedance tomography (EIT). Meanwhile, PAAm/PAA-Fe3+ double-network hydrogels were prepared as hydrogel pressure-sensitive substrates, and the feasibility of PAAm/PAA-Fe3+ hydrogels as sensitive elements for hydrogel pressure distribution sensors was confirmed through mechanical and electrical tests. Furthermore, based on the hydrogel pressure distribution sensor, a pressure distribution reconstruction model was obtained with a machine learning method. To verify the feasibility of the hydrogel pressure distribution sensor based on the EIT strategy, the hydrogel sensor was applied with forces of known location and magnitude. Then, the actual sensor acquisition data were reconstructed and compared with the applied force.

show abstract

Section: Materials and Methodsmentioning

confidence: 99%

Hydrogel Pressure Distribution Sensors Based on an Imaging Strategy and Machine Learning

Liu

Zhang

Yang

et al. 2021

ACS Appl. Electron. Mater.

View full text Add to dashboard Cite

show abstract

“…15,16 Convolutional neural networks (CNNs) were also proved to be feasible for ECT image reconstruction and improved image reconstruction has been achieved for the simple distributions with stationary objects in both simulation and experiment. [17][18][19] Although the type and structure of the network are vital for deep learning-based ECT image reconstruction, the dataset determines the measurement accuracy and generalization ability of the trained model. The model trained with the dataset only including the typical flow patterns is difficult to be used for the particle flow measurement in CFB.…”

Section: Zheng Et Al Proposed a Supervised Autoencoder Neural Network Tomentioning

confidence: 99%

“…Zheng et al proposed a supervised autoencoder neural network to solve the ECT image reconstruction problem for four typical flow patterns (annular, stratified, single bar, and two bar), where the dataset is obtained by numerical simulation 15,16 . Convolutional neural networks (CNNs) were also proved to be feasible for ECT image reconstruction and improved image reconstruction has been achieved for the simple distributions with stationary objects in both simulation and experiment 17–19 . Although the type and structure of the network are vital for deep learning‐based ECT image reconstruction, the dataset determines the measurement accuracy and generalization ability of the trained model.…”

Section: Introductionmentioning

confidence: 99%

Deep learning‐based tomographic imaging of ECT for characterizing particle distribution in circulating fluidized bed

Tang

Zhang

et al. 2023

AIChE Journal

View full text Add to dashboard Cite

The gas and solids in a circulating fluidized bed (CFB) are heterogeneously dispersed and a multiscale flow regime may form both in time and space. Accurate measurement of the fluidizing process is significant for investigating the multiscale gas–solid flow characteristics and the design, optimization, and control of CFBs in various applications. This article develops a deep learning‐based tomographic imaging of electrical capacitance tomography (ECT) to characterize the particle concentration distribution in a CFB. The deep tomographic imaging approach is realized through training a well‐designed convolutional neural network (CNN) with the numerically built dataset. Simulation results demonstrate that the average values of the relative image errors reconstructed by CNN in the test set are 0.1110 and 0.1114 for the 60 and 100 mm pipes, respectively, which are better than the average values of 0.1819 and 0.2519 by the Landweber algorithm. With the verification of the trained model based on the prepared data can image the unseen typical flow patterns better than Landweber, it is further used to investigate the particle flow characteristics of a lab‐scale CFB. Experimental results reveal that the developed deep tomographic imaging of ECT can successfully measure the fluidized particle distribution in both the 60 and 100 mm pipes, showing good prediction and generality of the designed CNN model. A flow regime transformation from “annular” flow to “core‐annular” flow and pneumatic conveying is observed under the tested conditions. Besides, the flow regime would be highly affected by the fluidized gas flow rate and the initial bed height.

show abstract

“…The need for tools that can compromise the trade-off between high quality reconstructed images and computational efficiency, is currently the main interest of machine learning (ML) [17,18], more specifically, deep neural network (DNN) methods [19]. DNN methods have been utilized in many fields due to their ability to map complex nonlinear functions [20,21]. DNN algorithms have been transferred and adapted such as in image reconstruction methods based on the convolutional neural network (CNN) [22], multi-scale CNNs [23], long short-term memory (LSTM) [24], and autoencoder [25].…”

Section: Introductionmentioning

confidence: 99%

Adversarial Resolution Enhancement for Electrical Capacitance Tomography Image Reconstruction

Deabes

Abdel-Hakim

Bouazza

et al. 2022

Sensors

View full text Add to dashboard Cite

High-quality image reconstruction is essential for many electrical capacitance tomography (CT) applications. Raw capacitance measurements are used in the literature to generate low-resolution images. However, such low-resolution images are not sufficient for proper functionality of most systems. In this paper, we propose a novel adversarial resolution enhancement (ARE-ECT) model to reconstruct high-resolution images of inner distributions based on low-quality initial images, which are generated from the capacitance measurements. The proposed model uses a UNet as the generator of a conditional generative adversarial network (CGAN). The generator’s input is set to the low-resolution image rather than the typical random input signal. Additionally, the CGAN is conditioned by the input low-resolution image itself. For evaluation purposes, a massive ECT dataset of 320 K synthetic image–measurement pairs was created. This dataset is used for training, validating, and testing the proposed model. New flow patterns, which are not exposed to the model during the training phase, are used to evaluate the feasibility and generalization ability of the ARE-ECT model. The superiority of ARE-ECT, in the efficient generation of more accurate ECT images than traditional and other deep learning-based image reconstruction algorithms, is proved by the evaluation results. The ARE-ECT model achieved an average image correlation coefficient of more than 98.8% and an average relative image error about 0.1%.

show abstract

Big Data driven U-Net based Electrical Capacitance Image Reconstruction Algorithm

Cited by 12 publications

References 7 publications

Hydrogel Pressure Distribution Sensors Based on an Imaging Strategy and Machine Learning

Hydrogel Pressure Distribution Sensors Based on an Imaging Strategy and Machine Learning

Deep learning‐based tomographic imaging of ECT for characterizing particle distribution in circulating fluidized bed

Adversarial Resolution Enhancement for Electrical Capacitance Tomography Image Reconstruction

Contact Info

Product

Resources

About