The application of rubberized concrete filled steel tube (RuCFST) structures can facilitate the recycling of used tires, offering a sustainable solution. In recent years, data-driven machine learning (ML) algorithms h...
详细信息
The application of rubberized concrete filled steel tube (RuCFST) structures can facilitate the recycling of used tires, offering a sustainable solution. In recent years, data-driven machine learning (ML) algorithms have garnered significant attention from researchers in the engineering field. However, the development of ML models for predicting the ultimate bearing capacity of RuCFST columns has been hindered by a lack of sufficient experimental data. To address this limitation, this study develops a novel ML framework aimed at accurately predicting the ultimate bearing capacity of RuCFST columns. This framework integrates an advanced tabular variational autoencoder (TVAE) data augmentation method and a Stacking ensemble strategy. The TVAE method generates reliable synthetic data to enhance the dataset, while the Stacking strategy integrates the strengths of various ML models, including Gradient Boosting Decision Tree, Extreme Gradient Boosting, Light Gradient Boosting Machine, Random Forest, and Ridge, to improve prediction accuracy. The predictive validity of the developed TVAE-Stacking model was assessed against other ensemble methods and commonly used machine learning models. The findings indicated that the TVAE-Stacking model excels in predicting the ultimate bearing capacity of RuCFST columns. This model serves as a valuable reference for applying RuCFST columns in structural engineering.
Production environments bring inherent system challenges that are reflected in the high-dimensional production data. The data is often nonstationary, is not available in sufficient size and quality, and is class imbal...
详细信息
Production environments bring inherent system challenges that are reflected in the high-dimensional production data. The data is often nonstationary, is not available in sufficient size and quality, and is class imbalanced due to the predominance of good parts. Data-driven manufacturing analytics requires data of sufficient quantity and quality. In order to predict quality characteristics, production data is collected across processes in the industrial use case at Bosch Rexroth AG for the purpose of inferring results in hydraulic final inspection using machine learning methods. Since high quality data generation is costly, synthetic data generation methodologies offer a promising alternative to improve prediction models and thus generate safer, more accurate predictions for manufacturing companies. Among the synthetic data generation methodologies used, variationalautoencoders compared to generative adversarial networks and synthetic minority oversampling technique methods are best suited to synthesize the feature with highest feature importance from a small sample data set compared to the production data and improve the prediction for the target variable.
暂无评论