Skill-based interpretation of noisy probe signals enhanced with a genetic algorithm

The paper presents the design and evaluation of an adaptive signal processi ng procedure based on human skill. The focus is on interpreting probe signa ls detected in gas-liquid flow in the presence of noise where existing sign al interpretation techniques may encounter difficulties. Interpretation of a probe signal requires construction of a corresponding two-state signal th at denotes the presence of the phases, i.e. gas and liquid, at the probe ti p. To develop a computer procedure that would imitate a skilled operator in probe signal interpretation, manual knowledge acquisition and evolutionary optimization were employed. First, a prototype signal interpretation proce dure based on operator skill was designed, and the procedure parameters wer e then optimized with a genetic algorithm. In the optimization process, a t wo-state signal reconstructed from the probe signal by an operator was used as a reference. The robustness of the approach was tested in a series of n umerical experiments. They included local evaluation on training and test s ignals, calculation of global void fraction values, and an assessment of va riability among different experts. The results showed that the developed te chnique is highly consistent with the operator way of signal interpretation and represents a reliable prerequisite for gas-liquid how measurements. (C ) 2000 Academic Press.