This study conducts a comparative electrochemical evaluation of three types of pearlitic steels used in flexible pipelines for oil transport in marine environments. The steels have been manufactured with chemical composition and geometry variations to optimize operation performance under adverse conditions. Electrochemical tests were conducted using solutions simulating marine environments with NaCl and CO₂, and at high temperatures. The results indicated that spheroidized (SC) steel demonstrated the best corrosion resistance under these specific conditions. Additionally, the Raman spectroscopy characterization technique was used to analyze the layers of corrosion products formed during the tests, identifying the presence of FeCO₃ (siderite) and other corrosive oxides. These discoveries are valuable for selecting and improving materials in flexible pipelines used in oil production in marine waters. The study highlights the importance of the cementite morphology present in pearlite as a relevant factor in the corrosive behavior of steels, contributing to the development of more efficient and durable solutions for the offshore oil and gas industry.

Physical simulation is a useful tool for examining the events that occur during the multiple stages of thermomechanical processing, since it requires no industrial equipment. Instead, it involves hot deformation testing in the laboratory, similar to industrial-scale processes, such as controlled hot rolling and forging, but under different conditions of friction and heat transfer. Our purpose in this work was to develop an artificial neural network (ANN) to optimize the thermomechanical behavior of stainless-steel biomaterial in a double-pass hot compression test, adapted to the Arrhenius–Avrami constitutive model. The method consists of calculating the static softening fraction (X_s) and mean recrystallized grain size (d_s), implementing an ANN based on data obtained from hot compression tests, using a vacuum chamber in a DIL 805A/D quenching dilatometer at temperatures of 1000, 1050, 1100 and 1200 °C, in passes (ε₁ = ε₂) of 0.15 and 0.30, a strain rate of 1.0 s⁻¹ and time between passes (t_p) of 1, 10, 100, 400, 800 and 1000 s. The constitutive analysis and the experimental and ANN-simulated results were in good agreement, indicating that ASTM F-1586 austenitic stainless steel used as a biomaterial undergoes up to X_s = 40% of softening due solely to static recovery (SRV) in less than 1.0 s interval between passes (t_p), followed by metadynamic recrystallization (MDRX) at strains greater than 0.30. At T > 1050 °C, the behavior of the softening curves X_s vs. t_p showed the formation of plateaus for long times between passes (t_p), delaying the softening kinetics and modifying the profile of the curves produced by the moderate stacking fault energy, γ_sfe = 69 mJ/m² and the strain-induced interaction between recrystallization and precipitation (Z-phase). Thus, the use of this ANN allows one to optimize the ideal thermomechanical parameters for distribution and refinement of grains with better mechanical properties.