Magnetic Flux Leakage Detection Technology for Well Casing on Neural Network

Well casing integrity is vital for the safe operations of oil wells, and also significant to detect well casing defects. Magnetic flux leakage (MFL) detection technology is widely-used in detecting the defects of various pipelines. Owing to the very complicated environment where well casing is laid in, the system which based on magnetic flux leakage technology is not mature yet to detect well casing defects. The technology of defects detection with RBF neural network based on Gaussian kernel is employed, by which parameters of well casing defects can be recognized. The training data samples were selected from both the simulated data sets for 3-D finite element model and measured MFL data. Detection system suitable to casing inspection is established. The experiment result indicates that defects of well casting can be detected and also its parameters can be identified effectively by detection system.