Research On Image Reconstruction And Development Of Software For Electrical Capacitance Tomography System

Process tomography (PT) technique is a new technique developed rapidly in recent years, which has great developmental potential and wide industrial application prospect in solving the measurement problem of multiphase flow. Electrical capacitance tomography (ECT) technique is a kind of PT technique based on the sensitive principle of capacitance, and it has been the most popular research direction and the main development technique of PT, due to its many distinct advantages such as no radiation, no invasion, high speed of response, simple structure, low cost, wide application range, better safety and so on. Though ECT has lots of advantages, there is still a lot of work to be done for practical use of the technique.Image reconstruction algorithm is an important factor to improve the image reconstruction quality in ECT system research. It reconstructs the medium distribution image of the measured area by limited observation data ,that is to gain the pixel-gray-scale value of image area . This is a non-linearity ,ill-posed inverse problems.In this article, the principle of BP neural network was introduced .The image reconstruction of 12-electrode ECT system based on BP neural networks was investigated .BP neural network is a kind of local approximation neural networks .In theory, it can approximate any continuous function if there is enough neural .The image reconstruction algorithm based on BP neural networks uses BP networks to build the mapping relationship between the capacitance value and the image gray-scale value .In this article , the numbers of hidden nodes of the BP neural networks was determined using dynamic adjust of changing structure method. Thus the BP neural networks converting the electrode capacitance measurements to the image gray-scale value was established.The BP neural networks for image reconstruction were trained in MATLAB environment. The training samples were obtained by using element method. Simulation experiment results indicate that the reconstruction algorithm based on BP networks can provide images superior to those obtained with the linear back-projection algorithm, with a similar reconstruction time.The upper-computer software is developed under the environment of Object-Oriented VC++, which implements the functions of receiving real-time data, reconstruction images online, saving capacitance values and review, and the like. LBP and BP networks algorithm are embedded in the software.