Application of neuro-fuzzy techniques in oil pipeline ultrasonic nondestructive testing

This paper presents a novel approach to the problem of nondestructive pipeline testing using ultrasonic imaging. The identification of the flaw type and its dimensions are the most important problems in the pipeline inspection. Unlike typical methods, a decision based neural network is used for the detection of flaws. We train a generalized regression neural network to determine the dimensions of the corrosions and generate the whole image of both the internal and external walls of the oil pipeline. As an improvement to the detection algorithm, we introduce fuzzy decision-based neural network algorithms for the detection and classification of the corrosions. The simulation and experimental systems results show that these new methods outperform the existing methods.