Fuzzy inference for two-phase gas-liquid flow type evaluation based on raw 3D ECT measurement data

Industrial diagnostic and monitoring systems still require new methods offering new possibilities of non-invasive observation and analysis of the two-phase gas-liquid mixture flows. This paper demonstrates an application of fuzzy methods for the purpose of the two-phase gas-liquid flow type evaluation. It has been demonstrated that the fuzzy inference using raw 3D Electrical Capacitance Tomography (ECT) measurement data and some contextual information such as gas and liquid flow stream in the two-phase mixture flow may be sufficient alternative to the methods commonly used in this field. A series of experiments has been completed using the test flow rig and the results of the recognition (human expert contra fuzzy inference) were compared. Fuzzy logic supported with the non-invasive 3D ECT measurement have proved to be suitable for the identification task applied for the dynamic two-phase flow processes ensuring the accuracy as good as the human expert work. However, the proper preparation of the inference system mechanism guarantees the high quality of the recognition results.