Accurate quality prediction can find and eliminate quality hazards. It is difficult to construct an accurate quality mathematical model for the production of small samples with high dimensionality due to the influence of quality characteristics and the complex mechanism of action. In addition, overfitting scenarios are prone to occur in high-dimensional, small-sample industrial product quality prediction. This paper proposes an ensemble learning and measurement model based on stacking and selects eight algorithms as the base learning model. The maximal information coefficient (MIC) is used to obtain the correlation between the base learning models. Models with low correlation and strong predictive power were chosen to build stacking ensemble models, which effectively avoids overfitting and obtains better predictive performance. To improve the prediction performance as the optimization goal, in the data preprocessing stage, boxplots, ordinary least squares (OLS), and multivariate imputation by chained equations (MICE) are used to detect and replace outliers. The CatBoost algorithm is used to construct combined features. Strong combination features were selected to construct a new feature set. Concrete slump data from the University of California Irvine (UCI) machine learning library were used to conduct comprehensive verification experiments. The experimental results show that, compared with the optimal single model, the minimum correlation stacking ensemble learning model has higher precision and stronger robustness, and a new method is provided to guarantee the accuracy of final product quality prediction.
This paper proposed a new method for supplier evaluation and selection after analysing the supplier state evolutionary process according to the entropy change process in the thermodynamics. In order to verify the feasibility of the new proposed method, we applied it to a maintenance, repair and overhaul/operation enterprise. Besides, we analysed the characteristics and problems of the maintenance, repair and overhaul/operation industry firstly, and then established an index system and calculated weights by balanced scorecard and analytic network process respectively. The results calculated by the proposed method are proved to be in accordance with the reality.
In Industry 4.0, data are sensed and merged to drive intelligent systems. This research focuses on the optimization of selective assembly of complex mechanical products (CMPs) under intelligent system environment conditions. For the batch assembly of CMPs, it is difficult to obtain the best combinations of components from combinations for simultaneous optimization of success rate and multiple assembly quality. Hence, the Taguchi quality loss function was used to quantitatively evaluate each assembly quality and the assembly success rate is combined to establish a many-objective optimization model. The crossover and mutation operators were improved to enhance the ability of NSGA-III to obtain high-quality solution set and jump out of a local optimal solution, and the Pareto optimal solution set was obtained accordingly. Finally, considering the production mode of Human–Machine Intelligent System interaction, the optimal compromise solution is obtained by using fuzzy theory, entropy theory and the VIKOR method. The results show that this work has obvious advantages in improving the quality of batch selective assembly of CMPs and assembly success rate and gives a sorting selection strategy for non-dominated selective assembly schemes while taking into account the group benefit and individual regret.
The study of superconductors' critical temperature (T c ) has been a matter of interest. A method combining a twolayer feature selection (TL) and Optuna-Stacking ensemble learning model is proposed in the study for predicting T c from physicochemical components. Since most machine-learning models require a large amount of prior knowledge to construct the feature vectors associated with T c manually, they may contain redundant or invalid features that adversely affect the analysis and prediction of T c . The TL model combines the advantages of filtered and packed feature selection. In the first layer, feature importance is ranked by "SHapley Additive explain (SHAP)" in combination with CatBoost, followed by maximum mutual information coefficient (MIC) and distance correlation coefficient (DCC) for initial feature selection in terms of feature importance ranking. The second layer uses a cross-validation-based genetic algorithm (cv-GA) to eliminate the remaining redundant/invalid features. The selected features are fed into the Stacking integrated learning model to achieve prediction of Tc, and the multidimensional hyperparametric optimization of the metamodel is achieved by Optuna, an improved Bayesian hyperparametric optimization framework based on the Tree-structured Parzen Estimator (TPE) and pruning strategy. The model has obvious advantages and generality in terms of prediction performance and feature reduction rate, and it also proves to be suitable for hightemperature superconductor T c prediction. It provides an efficient and cost-effective method for data-driven superconductor research.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.