Accurately estimating the fatigue strength of steels is vital, due to the extremely high cost (and time) of fatigue testing and often fatal consequences of fatigue failures. The main objective of this manuscript is to perform data mining on the fatigue dataset for steel available from the National Institute of Material Science (NIMS) MatNavi. The cross-industry process for data mining (CRISP-DM) approach was followed in the paper, in order to gain meaningful insights from the dataset and to estimate the fatigue strength of carbon and low alloy steels, using composition and processing parameters. Of the six steps of the CRISP-DM approach, special emphasis has been placed on steps 2 to 5 (i.e. data understanding, data preparation, modeling and evaluation). In step 4 (i.e. modeling), a range of machine learning (parametric and non-parametric) is explored to predict the fatigue strength, based on the composition and process parameters. Various algorithms were trained and tested on the dataset and finally evaluated, using metrics such as root mean square error (RMSE), Mean Absolute Error (MAE), Coefficient of Determination (R2) and Explained Variance Score (EVS).
A significant number of offshore structures and mechanical items installed in production systems on the Norwegian Continental Shelf (NCS) are either approaching or have exceeded their intended design life. However, with the help of the advancement of technology and analysis approaches, most of the offshore production facilities are being considered for life extension. This requires regular inspection, fitness for service (FFS) assessment, remnant life assessment, maintenance and repair (or modification). In this context, fatigue and fracture related degradation play a vital role. Hence, this paper discusses the state of the art as well as two major methodologies used for fatigue life prediction of structures and mechanical items. The first (S-N approach) is based on experimentally derived S-N curves and linear damage rule (LDR). Since LDR does not take sequence effect of loading into account the S-N approach often leads to overestimation / underestimation of fatigue life. Hence, this paper also takes into simultaneous consideration the second approach, which relies on the principles of fracture mechanics (FM) and crack growth analysis. Furthermore, the paper discusses damage tolerance analysis (DTA) and the role of Risk Based Inspection (RBI) to detect cracks before they grow to a critical level and cause catastrophic failure of the component. Thereafter, the paper discusses the reliability of Non-Destructive Evaluation (NDE) methods quantified in terms of Probability of Detection (PoD), to identify the flaw size and location. Finally, probabilistic crack growth (PCG) models used for remaining useful life estimation (RULE) and for planning inspection regimes of structural and mechanical items are discussed briefly.
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.