Prediction of the Transition-Temperature Shift Using Machine Learning Algorithms and the Plotter Database

Abstract

The long-term operating strategy of nuclear plants must ensure the integrity of the vessel, which is subjected to neutron irradiation, causing its embrittlement over time. Embrittlement trend curves used to predict the dependence of the Charpy transition-temperature shift, ΔT41J, with neutron fluence, such as the one adopted in ASTM E900-15, are empirical or semi-empirical formulas based on parameters that characterize irradiation conditions (neutron fluence, flux and temperature), the chemical composition of the steel (copper, nickel, phosphorus and manganese), and the product type (plates, forgings, welds, or so-called standard reference materials (SRMs)). The ASTM (American Society for Testing and Materials) E900-15 trend curve was obtained as a combination of physical and phenomenological models with free parameters fitted using the available surveillance data from nuclear power plants. These data, collected to support ASTM’s E900 effort, open the way to an alternative, purely data-driven approach using machine learning algorithms. In this study, the ASTM PLOTTER database that was used to inform the ASTM E900-15 fit has been employed to train and validate a number of machine learning regression models (multilinear, k-nearest neighbors, decision trees, support vector machines, random forest, AdaBoost, gradient boosting, XGB, and multi-layer perceptron). Optimal results were obtained with gradient boosting, which provided a value of R2 = 0.91 and a root mean squared error ≈10.5 °C for the test dataset. These results outperform the prediction ability of existing trend curves, including ASTM E900-15, reducing the prediction uncertainty by ≈20%. In addition, impurity-based and permutation-based feature importance algorithms were used to identify the variables that most influence ΔT41J (copper, fluence, nickel and temperature, in this order), and individual conditional expectation and interaction plots were used to estimate the specific influence of each of the features.

Parametric analysis of railway infrastructure for improved performance and lower life-cycle costs using machine learning techniques

“…• Decision Tree (DT) [86]: is a non-parametric supervised learning method used for classification and regression. • Random forest (RF) [87]: combine multiple "weak classifiers" (decision tree) into a single "strong classifier". • Gradient Boosting (GB): is a machine learning technique used for regression problems, which produces a predictive model in the form of an ensemble of weak prediction models.…”

Assessment of the Generalization Ability of the ASTM E900-15 Embrittlement Trend Curve by Means of Monte Carlo Cross-Validation

“…This analytical model includes 26 free parameters that were fitted using Maximum Likelihood Estimation (MLE) from the data. Relative to the calibration dataset, the model provides unbiased predictions and has a root mean square error (RMSE) of 13.32 • C and a coefficient of determination R 2 = 0.875 (other alternative correlations based on different datasets are introduced in [5]). ASTM E900-15 [3] adopts expression (7) (W: welds, P: plates and SRM plates, F: forgings) for the standard deviation, SD, which increases along with the predicted value of the TTS:…”

“…This dataset, therefore, represents the train set used to fit the 26 free parameters of the model. The variables that influence the TTS in this correlation are copper, nickel, phosphorus and manganese contents, irradiation temperature, neutron fluence, as well as the product type (forgings, plates, and SRM plates, and welds) [5]. The form of the correlation is semiempirical because even though the free parameters are fitted using statistical procedures, it includes two major embrittlement terms mechanistically guided that represent the hardening contribution from small microstructural defects and copper-enriched clusters created during irradiation [3].…”

Prediction of High-Temperature Creep Life of Austenitic Heat-Resistant Steels Based on Data Fusion

“…The essence of machine learning models constructed to predict material creep life is regression analysis. Commonly used regression modeling algorithms include the Support Vector Machine, Decision Tree, integrated learning, Gaussian Regression, and the BP Neural Network [29][30][31][32][33]. The Support Vector Machine uses kernel functions and non-linear transformations to achieve linear divisibility in high-dimensional spaces and solves the classification problems in high-dimensional spaces.…”