Fuzzy mathematical modeling for reconstructing images in ECT of manufacturing processes

Electrical capacitance tomography (ECT) is a well known technique for process tomography. ECT was considered as a non-invasive, low cost technique for solving wide range of manufacturing problems in casting industry. ECT image reconstruction is still an urgent problem that has not been well solved due to the influence of soft-field in the ECT system. Although there are many algorithms to solve the image reconstruction problem, these algorithms are not yet able to provide a single mathematical model which can provide a relationship between pixels in images and sensor measurements. In order to improve the quality of ECT reconstructed image, we propose the use of fuzzy mathematical modeling to handle the ECT for imaging conductive materials. This problem is known as the ECT inverse problem. The proposed methodology is based on building a Fuzzy Inference System (FIS) to predict the metal fill distribution during the filling process. The designed fuzzy model uses a training based methodology for evaluating the parameters of antecedents and consequents of Takagi-Sugeno (TS) fuzzy systems. Several cases for metal fill using one or multiple fill points were considered with promising results.