The paper presents a review of current achievements in the Electrical Capacitance Tomography (ECT) in relation to its possible applications in the study of phenomena occurring in fluidised bed reactors. Reactors of that kind are being increasingly used in chemical engineering, energetics (fluidised bed boilers) or industrial dryers. However, not all phenomena in the fluidised bed have been thoroughly understood. This results in the need to explore and develop new research methods. Various aspects of ECT operation and data processing are described with their applicability in scientific research. The idea for investigation of temperature distribution in the fluidised bed, using multimodal tomography, is also introduced. Metrological requirements of process tomography such as sensitivity, resolution, and speed of data acquiring are noted.

A new approach to solve the inverse problem in electrical capacitance tomography is presented. The proposed method is based on an artificial neural network to estimate three different parameters of a circular object present inside a pipeline, i.e. radius and 2D position coordinates. This information allows the estimation of the distribution of material inside a pipe and determination of the characteristic parameters of a range of flows, which are characterised by a circular objects emerging within a cross section such as funnel flow in a silo gravitational discharging process. The main advantages of the proposed approach are explicitly: the desired characteristic flow parameters are estimated directly from the measured capacitances and rapidity, which in turn is crucial for online flow monitoring. In a classic approach in order to obtain these parameters in the first step the image is reconstructed and then the parameters are estimated with the use of image processing methods. The obtained results showed significant reduction of computations time in comparison to the iterative LBP or Levenberg-Marquard algorithms.

This paper presents a study on applying machine learning algorithms for the classification of a two-phase flow regime and its internal structures. This research results may be used in adjusting optimal control of air pressure and liquid flow rate to pipeline and process vessels. To achieve this goal the model of an artificial neural network was built and trained using measurement data acquired from a 3D electrical capacitance tomography (ECT) measurement system. Because the set of measurement data collected to build the AI model was insufficient, a novel approach dedicated to data augmentation had to be developed. The main goal of the research was to examine the high adaptability of the artificial neural network (ANN) model in the case of emergency state and measurement system errors. Another goal was to test if it could resist unforeseen problems and correctly predict the flow type or detect these failures. It may help to avoid any pernicious damage and finally to compare its accuracy to the fuzzy classifier based on reconstructed tomography images – authors’ previous work.