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.
In this work the esterification of diethyl tartrate was studied. The research was focused on the enhancement of reversible reaction yield, which is accomplished by dewatering of the reaction mixture. The removal of water shifts the equilibrium towards the main product. Pervaporation was applied for this purpose, and results were compared to distillation. The advantages and limitations of both processes are discussed. The experimental part consists of dewatering of mixture after the reaction had reached the equilibrium, and was subsequently fed to the test rig equipped with a single zeolite membrane purchased from Pervatech B.V. Results show a significant conversion increase as a result of water removal by pervaporation. Compared to distillation no addition of organics is necessary to efficiently remove water above the azeotrope. Nevertheless, some limitations and issues which call for optimisation are pointed out. A simple numerical model is proposed to support design and sizing of the pervaporation system. Various modes of integrated system operation are also briefly discussed.