Duplex stainless steels, with ferritic-austenitic microstructure, have excellent mechanical properties and corrosion resistance. However, when duplex stainless steels are exposed to temperatures between 600 and 1000 °C, some phase transformations can occur such as chromium nitrides precipitation, chromium carbides precipitation and the sigma phase formation. The formation of such compounds leads to loss in both corrosion resistance and fracture toughness. The negative effects of the formation of chromium nitrides, carbides and the sigma phase are due to the chromium depletion in the matrix. The phase transformations cited above occur initially at ferritic-austenitic interfaces and at the grain boundaries. The aim of this work is to identify and characterize the phase transformations, which occur when aging heat treatments are carried out at temperatures at which the kinetics is the fastest for the reactions mentioned. At first, the samples were annealed at 1100 °C for 40 min. The aging heat treatments were then carried out at 850 °C for 6, 40 e 600 min. Microstructural characterization was done by using optical microscopy with different etchings, in order to identify each phase formed in the duplex stainless steel during aging heat treatments. The toughness was also evaluated by using Charpy impact test. Impact tests show that loss of toughness was related to phase transformations

The coefficient of friction (CoF) obtained from tribological tests conducted on textured and porous surfaces was analysed using the machine learning Radial Basis Function (RBF) method. Non-textured and non-porous samples were taken as reference surfaces. Test parameters, such as entrainment velocity and slide-roll ratio (SRR), along with geometric characteristics of surface features (e.g. texture width and depth, coverage area, circularity, spatial distribution and directionality, among others), were selected as training dataset for the machine learning RBF model. The surface features were divided into designed patterns (dimples and grooves) manufactured by laser texturing, and randomised cavities (surface pores) resulted from the sintering process. The principal outcomes of this study are the effective use of the machine learning RBF method for tribological applications, as well as a critical discussion on its feasibility for the experimental dataset selected and the preliminary results obtained. Main results show that the Hardy multiquadric radial basis function provided an overall correlation coefficient of 0.934 for 35 poles. The application of the suggested machine learning technique and methodology can be extended to other experimental results available in the literature to train more robust models for predicting tribological performances of textured and structured surfaces.