Wykaz obszarów badawczych związanych z tagiem Electrical-capacitance-tomography:
| # | Obszar badawczy | Dziedzina naukowa |
|---|---|---|
| 1 |
“Deep neural networks for image reconstruction in electrical capacitance tomography” Electrical capacitance tomography (ECT) enables the visualization of the spatial distribution of an object’s electrical permittivity. Image reconstruction in ECT presents a significant challenge as it is an ill-posed and ill-conditioned inverse problem. Advanced nonlinear algorithms, such as the Levenberg-Marquardt method, are iterative and computationally intensive, primarily due to the repeated calculation of the Jacobian matrix. Deep neural networks (DNNs) have emerged as a promising alternative for image reconstruction. This work will explore deep network architectures that not only match but significantly outperform classical methods in reconstruction quality. Synthetic data will be employed for supervised learning, and the performance of DNNs will be tested against real measurements. Application-specific training datasets will be analyzed, and their size will be expanded using data augmentation techniques. A comparative evaluation of various training datasets will also be conducted. To optimize the network, different loss functions and solvers will be utilized. Reconstructed images will be generated using DNNs and compared against a baseline provided by the Levenberg-Marquardt algorithm. Results will be assessed using selected image quality metrics. It is anticipated that deep networks will enhance the spatial resolution of ECT scanners. The insights gained from selecting deep networks, analyzing their architectures, and refining training strategies can potentially be applied to solve inverse problems in other fields.
|
|
| 2 |
High-Spatial Resolution Electrical Capacitance Tomography Electrical capacitance tomography (ECT) is a non-invasive imaging technique that reconstructs the spatial distribution of electrical permittivity from capacitance measurements at the interface of the object being examined. Since its introduction, ECT has been extensively studied, particularly in industrial process monitoring, multiphase flow imaging, and process tomography. Current research focuses on improving image quality through sensor and front-end electronics design, iterative model-based algorithms, regularization, statistical methods, and, more recently, machine learning methods. The image spatial resolution of ECT remains fundamentally limited by the small number and relatively large size of sensing electrodes, the non-uniform spatial sensitivity distribution, and the nonlinear nature of the inverse problem. Increasing the number of electrodes can provide additional measurement information, but it also poses significant challenges related to measurement accuracy, signal-to-noise ratio, and system complexity. Consequently, most state-of-the-art electrical capacitance tomography systems still use a small number of electrodes and provide relatively low-resolution images. Recent research is increasingly exploring new sensor geometries, optimized electrode configurations, advanced capacitance measurement electronics, and data-driven reconstruction methods. However, it has not yet been possible to demonstrate that increasing the nominal number of sensing elements effectively improves spatial resolution. The proposed research addresses this gap by examining electrodes synthesized from densely arranged electrode segments, advanced measurement strategies, numerical modeling, and dedicated reconstruction methods. A combined numerical and experimental approach will be used to determine the physical and technological limitations of high-spatial-resolution ECT and to develop design principles for next-generation ECT sensors.
|