Abstract

The ferrite content of 202 austenitic stainless-steel welds was predicted based on Machine Learning (ML), and the data set was analysed by manifold learning, feature engineering, and other methods. Multiple ML methods such as K-Nearest Neighbors (KNN), Support Vector Regression (SVR), Ensemble Learning (EL)、Multiple model Merging (MM), and Artificial Neural Network (ANN) performed algorithm model building and model tuning on the data set and evaluated the prediction performance of the model. The ML visualization and ML interpretation tools are used to demonstrate in detail the comparison of the prediction performance of ferrite number (FN) of various ML models and the effect of welding parameters on FN prediction. SVR, Gradient Boost, Xgboost, Catboost, Voting, Stacking, and MLP regression models demonstrate precision prediction and generalization. The coefficient of determination ( R 2 ) of the MLP model was 0.956 on the test set, which showed generalization and robustness. The visual data analysis and ML sample tracking methods are used to optimize the model. An ANN model with high prediction accuracy was proposed, and the R 2 of the test set was 0.972. This paper reveals the comprehensive application of ML-assisted material design and data sample visual tracking in the field of materials. • PyTorch deep learning framework to improve prediction accuracy. • Welding parameters are used to analyse welding parameters’ effect on ferrite content in welds. • 13 kinds of algorithms are selected for modelling and training. • Visualization tools explain the model prediction and feature importance. • The determination coefficient of the neural network model is 0.972.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call