Signal processing and defect analysis of pipeline inspection applying magnetic flux leakage methods

Abstract

Corrosion, stresses and mechanical damage of oil and gas pipelines can result in catastrophic failures, so pipeline safety evaluation is an important problem of oil and gas transmission. To evaluate the pipeline safety, this paper described a novel magnetic flux leakage (MFL) inspection device, and the designing MFL intelligent inspection pig was used to multi-radius pipelines and variational work condition. At the same time, because signal processing and defect recognition technique is one of the most important techniques in offshore pipeline inspection MFL system, the paper also discussed its signal processing procedure. Time-frequency analysis, median and adaptive filter, and interpolation processing are adopted to preprocess MFL inspection signal. In order to obtain high sensitivity and precision, we adopted multi-sensor data fusion technique. A wavelet basis function neural network was used to recognize defect parameters. The main contribution of the article is that we presented a novel method to evaluate and predict oil pipelines’ condition through combining neural network, data fusion and expert system techniques, and through constructing a knowledge-based off-line inspection expert system, the system improved its defect recognition capability greatly.