Three dimensional evaluation of parallelepiped flaw using amorphous MI sensor and neural network in biaxial MFLT

In this paper, we attempt to evaluate the three dimensional shape of a parallelepiped flaw including its location, i.e., the horizontal position and the located surface, by biaxial Magnetic Flux Leakage Testing with neural network. The specimen is a magnetic material subjected to the magnetic field, and the magnetic flux in the specimen leaks near the flaw. We measure the biaxial Magnetic Flux Leakage, i.e., the tangential and the normal components of MFL by an amorphous Magneto-Impedance sensor. The amorphous MI sensor has the wide measurement range, high sensitivity and high spacial resolution, so that it is suitable for precise qualitative estimation by MFLT. We extract Characteristic Quantities from the one dimensional biaxial MFL distributions on each scanning line by Approximate Analytical Method. The horizontal position of a flaw along the scanning line is presented by some of the CQs. Neural network is used to predict the shape of the cross section of the flaw beneath each scanning line, i.e., the width, the depth including the located surface from the CQs. By repeating a similar process along several scanning lines parallel to the specimen surface, we can identify the three dimensional shape of the flaw. The neural network is found to be able to evaluate the three dimensional shape of unknown flaws in a good accuracy.