Industrial process tomography (IPT) based process control is an advisable approach in industrial heating processes for improving system efficiency and quality. When using it, appropriate dataflow pipelines and visualizations are key for domain users to implement precise data acquisition and analysis. In this article, we propose a complete data processing and visualizing workflow regarding a specific case—microwave tomography (MWT) controlled industrial microwave drying system. Furthermore, we present the up-to-date augmented reality (AR) technique to support the corresponding data visualization and on-site analysis. As a pioneering study of using AR to benefit IPT systems, the proposed AR module provides straightforward and comprehensible visualizations pertaining to the process data to the related users. Inside the dataflow of the case, a time reversal imaging algorithm, a post-imaging segmentation, and a volumetric visualization module are included. For the time reversal algorithm, we exhaustively introduce each step for MWT image reconstruction and then present the simulated results. For the post-imaging segmentation, an automatic tomographic segmentation algorithm is utilized to reveal the significant information contained in the reconstructed images. For volumetric visualization, the 3D generated information is displayed. Finally, the proposed AR system is integrated with the on-going process data, including reconstructed, segmented, and volumetric images, which are used for facilitating interactive on-site data analysis for domain users. The central part of the AR system is implemented by a mobile app that is currently supported on iOS/Android platforms.

The article presents an application of microwave tomography (MWT) in an industrial drying system to develop tomographic-based process control. The imaging modality is applied to estimate moisture distribution in a polymer foam undergoing drying process. Our Leading challenges are fast data acquisition from the MWT sensors and real-time image reconstruction of the process. Thus, a limited number of sensors are chosen for the MWT and are placed only on top of the polymer foam to enable fast data acquisition. For real-time estimation, we present a neural network-based reconstruction scheme to estimate moisture distribution in a polymer foam. Training data for the neural network is generated using a physics-based electromagnetic scattering model and a parametric model for moisture sample generation. Numerical data for different moisture scenarios are considered to validate and test the performance of the network. Further, the trained network performance is evaluated with data from our developed prototype of the MWT sensor array. The experimental results show that the network has good accuracy and generalization capabilities.

Microwave tomography (MWT) based control is a novel idea in industrial heating systems that demands fast DAQ and real-time imaging algorithms. Uniform diffraction tomography (UDT) is one such technique that can provide real-time imaging. However, its single-input single-output data based inverse scattering formulation can lead to time-consuming DAQ. In this article, a multistatic uniform diffraction tomography (MUDT) imaging algorithm is proposed for a fixed array MWT system. The MWT system is integrated into the industrial heating unit HEPHAISTOS to estimate the moisture distribution in a polymer foam. In addition, a technique is presented to retrieve the electrical properties of the targets using reconstructed information from MUDT and by investigating the singular values of multistatic scattering data. Through numerical and experimental data for the considered moisture scenarios, the MUDT approach is tested, and its comparison with the UDT approach is shown. Reconstructed results show that in comparison to UDT, the MUDT approach i) eliminates the need for mechanical scanning, ii) provides aliasing-free images by following Nyquist sampling criteria, and iii) can resolve multiple targets in the imaging media with significant improvement in the spatial resolution that further augments in the correct retrieval of the dielectric constants of the target.

Microwave tomography (MWT) based control is a novel idea in industrial heating systems for drying polymer foam. In this work, an X-band MWT module is designed and developed using a fixed antenna array configuration and integrated with the HEPHAISTOS industrial heating system. A decomposition of the time-reversal operator (DORT) algorithm with a proper Green’s function of multilayered media is utilized to localize the moisture location. The derived Green’s function can be applied to the media with low or high contrast layers. It is shown that the time-reversal imaging (TRI) with the proposed Green’s function can be applied to the multilayered media with a moderately rough surface. Moreover, a single frequency TRI is proposed to decrease the measurement time. Numerical results for different moisture scenarios are presented to demonstrate the efficacy of the proposed method. The developed method is then tested on the experimental data for different moisture scenarios from our developed MWT experimental prototype. Image reconstruction results show promising capabilities of the TRI algorithm in estimating the moisture location in the polymer foam.

When using the statistical inversion framework in microwave tomography (MWT), generally, the real and imaginary parts of the unknown dielectric constant are treated as uncorrelated and independent random variables. Thereby, in the maximum a posteriori estimates, the two recovered variables may show different structural changes inside the imaging domain. In this work, a correlated sample-based prior model is presented to incorporate the correlation of the real part with the imaginary part of the dielectric constant in the statistical inversion framework. The method is used to estimate the inhomogeneous moisture distribution (as dielectric constant) in a large cross section of polymer foam. The targeted application of MWT is in industrial drying to derive intelligent control methods based on tomographic inputs for selective heating purposes. One of the features of the proposed method shows how to integrate lab-based dielectric characterization, often available in MWT application cases, in the prior modeling. The method is validated with numerical and experimental MWT data for the considered moisture distributions.