Intelligent monitoring approach for pipeline defect detection from MFL inspection

Artificial Neural Networks(ANNS) have top level of capability to progress the estimation of cracks in metal tubes. The aim of this paper is to propose an algorithm to identify modeled cracks by magnetic flux leakage inspection in Non Destructive Testing (NDT) [1, 2, 3, 4, 5, and 6]. The analysis is carried out with a simulated database of signals in which the depth of the crack, its width, shape, And geometric dimension of the detection process, is allowed to change. The simulated signal is input to the network, after a reduction process in which the main features of the signal are extracted. Feature extractors are used in pattern recognition area due to their advantages in representing data. With this approach classifier's job became easier and more effective. The main goal of the feature extractor is to reflect the characteristics of an object in a given dataset. In this way feature extractor simplify the amount of resources required to describe a large dataset accurately. This paper presents the results of employing different kinds of feature extraction functions and classification and provides compression between them. As the output of ANN, we shall justify if any care in meta lto indicate whether the input signal is crack or not. The analysis based on the neural network and feature extractor functions is shown to be quite top probability of detection.