For estimation of monthly precipitation, considering the intricacy and lack of accurate knowledge about the physical relationships, black box models usually are used because they produce more accurate values. In this article, a hybrid black box model, namely ANN-RBF, is proposed to estimate spatiotemporal value of monthly precipitation. In the first step a Multi Layer Perceptron (MLP) network is used for temporal estimation of monthly precipitation using the value of precipitation in previous months in the same gauging station. In the second step, Radial Basis Function (RBF) is used to estimate the value of precipitation in specific month and a spatial point within the study region, considering the value of monthly precipitation in other stations. In this regard, three commonly used RBFs' Multi Quadric (MQ), Inverse Multi Quadric (IMQ) and Gaussian (Ga), are used for spatial estimation. Finally, the combination of these two steps leads to ANN-RBF hybrid model. The model is examined using monthly precipitation data of Ardabil plain located north western of Iran. All results show the reliable accuracy of ANN-RBF model for spatiotemporal estimation of precipitation. Furthermore, IMQ RBF yields more accurate results for spatial estimation in comparison with two other RBFs. The crossvalidation scheme was also employed to validate the spatial estimation performance of the proposed model.
In this study, the hydrogen embrittlement and corrosion behavior of X100 pipeline steel (Ref) was investigated after various heat treatments, including one-step austenitizing at 880 °C (HT3), 830 °C (HT2), and 780 °C (HT1) for 90 min, oil quenching to room temperature, tempering at 600 °C for 30 min, and air cooling to room temperature. Potentiodynamic polarisation was performed to assess the electrochemical corrosion behavior, while the Charpy impact test and Vickers microhardness measurement were performed to assess the hydrogen embrittlement susceptibility before and after hydrogen charging. SEM, EBSD, and EDS were used to further characterize the fractured surface and crystallographic texture of specimens, while XRD was used to evaluate the macro-texture and corrosion products. The results of the Charpy impact and hardness tests showed that the high hardness and low impact energy values in the Reference and HT3 specimens were linked to a higher susceptibility to hydrogen embrittlement, indicating that the hardness values and Charpy impact energy, respectively, increased and decreased with a decrease in the hydrogen embrittlement resistance. The micro-texture results from the EBSD analysis showed that the HT3 and Ref. specimens had higher Kernel average misorientation (KAM) values and higher deformed grains fractions than those of the HT2 and HT1 specimens, resulting in lower corrosion resistance. The HT2 specimen had an optimal combination of beneficial ({110}, {111}, {332}) and harmful texture components ({100}), showing that corrosion resistance can be improved.
Nowadays, an increasing number of oil and gas transmission pipes are constructed with high-strength low alloy steels (HSLA); however, many of these pipelines suffer from different types of hydrogen damages, such as hydrogen-induced cracking (HIC). So many research efforts are being carried out to reduce the detrimental effects of hydrogen damage in HSLA steel pipes. The thermomechanical control process (TMCP) is a microstructural control technique that is able to eliminate the conventional heat treatment after hot rolling. Recent research demonstrated that TMCP provides high HIC resistance without adding high amounts of alloying elements or expensive heat treatments. However, once these HSLA steel pipes are put into service, they experience HIC damage, and the prediction of its kinetics is a necessary condition to perform Fitness-For-Service assessments. To develop a reliable predictive model for the kinetics of HIC, the relations among the microstructural features, environmental parameters, and mechanical properties have to be fully understood. This paper presents a review of the key metallurgical and processing factors to develop HSLA steel pipes, as well as a review of the phenomenological and empirical models of HIC kinetics in order to identify specific research directions for further investigations aimed to establish a reliable and sound model of HIC kinetics.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.