Duplex stainless steels present excellent mechanical and corrosion resistance properties. However, when heat treated at temperatures above 600 • C, the undesirable tertiary sigma phase is formed. This phase presents high hardness, around 900 HV, and it is rich in chromium, the material toughness being compromised when the amount of this phase is not less than 4%. This work aimed to develop a solution for the detection of this phase in duplex stainless steels through the computational classification of induced magnetic field signals. The proposed solution is based on an Optimum Path Forest classifier, which was revealed to be more robust and effective than Bayes, Artificial Neural Network and Support Vector Machine based classifiers. The induced magnetic field was produced by the interaction between an applied external field and the microstructure. Samples of the 2205 duplex stainless steel were thermal aged in order to obtain different amounts of sigma phases (up to 18% in content). The obtained classification results were compared against the ones obtained by Charpy impact energy test, amount of sigma phase, and analysis of the fracture surface by scanning electron microscopy and X-ray diffraction. The proposed solution achieved a classification accuracy superior to 95% and was revealed to be robust to signal noise, being therefore a valid testing tool to be used in this domain.

Conventional manufacturing processes cause plastic deformation that leads to magnetic anisotropy in processed materials. A deeper understanding of materials characterization under rotational magnetization enables engineers to optimize the overall volume, mass, and performance of devices such as electrical machines in industry. Therefore, it is important to find the magnetic easy direction of the magnetic domains in a simple and straightforward manner. The Magnetic easy direction can be obtained through destructive tests such as the Epstein frame method and the Single Sheet Tester by taking measurements in regions of irreversible magnetization usually called domains. In the present work, samples of rolled SAE 1045 steel (formed by perlite and ferrite microstructures) were submitted to induced magnetic fields in the reversibility region of magnetic domains to detect the magnetic easy direction. The magnetic fields were applied to circular samples with different thicknesses and angles varying from 0 • to 360 • with steps of 45 • . A square sample with a fixed thickness was also tested. The results showed that the proposed non-destructive approach is promising to evaluate the magnetic anisotropy in steels independently of the geometry of the sample. The region studied presented low induction losses and was affected by magnetic anisotropy, which did not occur in other works that only took into account regions of high induction losses.